ElevenLabs introduces audio tags for precise emotional control
Imagine an AI voice that can whisper secrets, burst into genuine laughter, express rage, or convey heartbreak with the same emotional depth as a seasoned actor. What sounds like science fiction became reality on June 5, 2025, when ElevenLabs released v3 Alpha – the most expressive text-to-speech model ever created.
This isn’t just another incremental update. ElevenLabs v3 represents a paradigm shift from mechanical speech synthesis to emotional performance. For the first time in AI history, machines don’t just read text – they perform it with human-like emotion, timing, and nuance that can fool even trained audio professionals.
Introduction to Eleven v3
ElevenLabs v3 (Alpha) is the latest and most advanced text-to-speech model from ElevenLabs, and it’s making waves among content creators. Imagine being able to direct an AI voice actor with stage cues like [whisper] or [laughs], or having multiple AI characters carry on a conversation with natural timing and emotion. This is exactly what ElevenLabs v3 promises – a leap from simple robotic readings to AI-generated performances.
In this comprehensive guide, we’ll explore what sets ElevenLabs v3 apart, how to harness its new features, and what it means for creators in fields from podcasting to game development. Whether you’re a video editor looking to add compelling narration, an indie game designer creating character dialogue, or an educator making multilingual content, ElevenLabs v3 offers tools to elevate your projects. We’ll dive into the model’s core innovations like audio tags for fine-grained emotional control and a dialogue mode that can weave multiple voices into a seamless conversation. You’ll learn best practices for getting the most out of this model – from prompt engineering and voice selection to using the new features effectively.
We’ll also share creative examples (humorous, emotional, and action-packed) to spark your imagination, and discuss how ElevenLabs v3 integrates into workflows with popular tools like Adobe Premiere Pro, After Effects, and Audition. By the end of this article, you’ll have a thorough understanding of ElevenLabs v3 (Alpha) – what it is, how to use it, and why it’s a game-changer for AI voice generation. Let’s start with an overview of this new model and how it builds upon previous versions.
Eleven v3 - Performance Specifications
| Specification | ElevenLabs v3 Alpha | ElevenLabs v2 / v2.5 |
|---|---|---|
| Supported Languages | 70+ (including regional variants) | 29-33 |
| API Character Limit | 10000 per request | 10000 |
| Audio Tag Support | Full inline control | None |
| Emotional Range | Exceptional (9.2/10) | Good (6.5/10) |
| Multi-Speaker Support | Native dialogue generation | Manual mixing only |
| Processing Time | 1-3 seconds (Alpha) | 300-500ms |
| Real-time Capability | Coming soon | Available (v2.5) |
ElevenLabs v3 (Alpha) is the company’s most expressive text-to-speech model yet, representing a major upgrade over its earlier versions. It’s built on a new architecture designed to deliver unprecedented realism and control in generated speech. The goal of v3 is to enable AI voices that do more than just read text – they perform it. This means the AI can convey nuanced emotions, change tone or speaking style mid-sentence, and even handle multiple speaking roles in one go without breaking the flow. In practical terms, v3’s outputs sound more human-like in quality and can carry the rhythm and emotional dynamics of real conversations.
Overview of ElevenLabs v3 (Alpha)
- For starters, it introduces inline audio tags – special directives in your script that let you control emotions, delivery, and even sound effects in the generated speech. Earlier models (v2, v2.5) offered only basic controls like pauses or simple intonation changes, but v3 opens up a much richer palette of expression. Another big addition is the new Dialogue Mode, which allows multiple AI voices to speak within one generated clip, interacting as if in a natural conversation. Previous versions could only generate one voice at a time, so any dialogue had to be stitched together manually; v3 can handle it in one pass with coherent context shared between speakers.
- ElevenLabs v3 also dramatically expands language support. While v2 was limited to around 20–30 languages (29 languages to be exact), v3 supports over 70 languages, covering the vast majority of the world’s population. This means you can generate speech in languages ranging from English, Spanish, and Chinese to Icelandic, Swahili, and Welsh – all with the same expressive capabilities. The model is truly global in reach, enabling creators to easily produce multilingual content.
- Another improvement is in the voice quality and emotional range. The voices produced by v3 sound more natural and lifelike than ever – often indistinguishable from real human speech in tone and flow. The model can shift its emotion or speaking style on the fly (for example, start a sentence calmly and end it in a shout) thanks to the new tags system. This kind of dynamic expressiveness was not possible with the monotone outputs of older TTS systems. ElevenLabs v3’s speech has a broad dynamic range that can convey subtle nuances in emotion, emphasis, and pacing that make the narration feel like a performance rather than a flat reading.
It’s important to note that ElevenLabs v3 is currently in public alpha release. In other words, it’s a research preview available for anyone to try, but it’s still being refined. The outputs can be breathtakingly realistic when everything works well, but the model may require more prompt engineering and tweaking compared to earlier versions to get optimal results.
Due to its complexity, v3 also has higher latency – it takes a bit longer to generate audio – which means it’s not yet suitable for real-time applications like live conversational AI (for now, ElevenLabs recommends using their faster v2.5 models for real-time needs). The team is actively working on a real-time version of v3, as well as improving its reliability and consistency during this alpha phase.
In summary, ElevenLabs v3 (Alpha) is a major leap forward in text-to-speech technology. It brings creative controls (through tags and dialogue), enhanced quality, and multilingual reach that were previously unheard of in one package. Next, we’ll take a closer look at each of v3’s core new features and what they mean for users.
| Feature | ElevenLabs v3 | Google Cloud TTS | Amazon Polly | Microsoft Azure | OpenAI Whisper |
|---|---|---|---|---|---|
| Audio Tag Support | 40+ tags | None | None | None | N/A (STT only) |
| Emotional Range | Exceptional | Limited | Basic | Moderate | N/A |
| Multi-Speaker Dialogue | Native | Manual only | Manual only | Manual only | N/A |
| Language Count | 70+ | 100+ | 60+ | 75+ | 99 |
| Voice Customization | Deep cloning | Limited | Basic | Moderate | N/A |
| Real-time Capability | Coming soon | Yes | Yes | Yes | Yes |
| Cost per Character | 0.2 credits (Alpha) | $4/1M chars | $4/1M chars | $4/1M chars | $0.006/min |
| Naturalness Score | 9.4/10 | 7.8/10 | 7.2/10 | 8.1/10 | N/A |
New Key Features of ElevenLabs v3
ElevenLabs v3 introduces several groundbreaking features that distinguish it from prior versions. Below is an overview of these core innovations and how they work:
- Audio Tags for Emotional Control: The headline feature of v3 is its support for inline audio tags embedded in your text. By placing instructions in square brackets (e.g., [laughing], [angry], [whispers]), you can guide the model’s delivery in fine detail. These tags cover emotions (happy, sad, angry, etc.), delivery styles (whispering, shouting), non-verbal sounds (laughter, sighs), and even environmental sounds or scene context. For example, you could write a sentence like: I can’t believe it [laughs] this is amazing! and the voice will actually include a natural laugh in the middle. Audio tags allow dynamic shifts in tone mid-sentence without breaking the flow, something not possible in earlier models. We’ll explore the full depth of audio tags and how to use them shortly.
- Multi-Speaker Dialogue Mode: ElevenLabs v3 can generate conversations with multiple speakers in one go. Its new dialogue mode lets you assign different voices to different lines or characters, enabling seamless back-and-forth exchanges that sound like real dialogue. The model handles interruptions, overlapping speech, and emotional interplay between speakers in a very natural way. For instance, one character can excitedly interrupt another, or two voices can react to the same event with appropriate timing. All speakers share context, meaning the AI keeps track of the conversation’s flow and tone, making the interaction coherent and realistic. Previously, if you wanted a dialogue, you had to generate each voice separately and manually splice them; v3 automates that by weaving voices together into a single audio scene. This feature is a game-changer for creating radio-play style content, podcasts with multiple virtual hosts, or character dialogues in stories and games.
- Enhanced Voice Quality and Expressiveness: The overall quality of voices in v3 has been elevated. The speech outputs are more human-like in their pacing, intonation, and clarity. There’s a noticeable improvement in the expressiveness – voices can convey subtle emotions like sarcasm, hesitation, or excitement far more convincingly than before. ElevenLabs calls v3 “the most expressive text-to-speech model ever,” offering full control over not just the words but how they’re delivered. The model can modulate its delivery in real time, reacting to cues in the text. This means you get more nuanced performances rather than a mechanical recital. For example, you can have a sentence start with a bored tone and crescendo into enthusiasm by the end, purely through text cues. The end result is audio that can carry a story or message with emotional weight, engaging listeners on a deeper level. (Under the hood, this expressiveness comes from training on a wide range of speech patterns and the new tag-driven prompting system that allows dynamic changes).
- 70+ Language Support: With v3, ElevenLabs has expanded its language repertoire from 33 languages to over 70 languages, a huge jump that opens up many possibilities. You can seamlessly switch between languages in the same script, or generate content in languages that were previously unavailable. Major world languages like English, Spanish, Mandarin Chinese, Arabic, Hindi, French, and Portuguese are supported, as well as a plethora of others (Polish, Indonesian, Korean, Vietnamese, Greek, Swedish – you name it). This broad language support means creators can localize their content to reach diverse audiences with authentic-sounding voices. Not only does v3 speak the language, but it does so with the appropriate accent and intonation patterns for each language, thanks to its advanced training. You could have a single AI voice narrate an audiobook and naturally voice characters in different languages where needed, or create a multilingual customer service hotline that speaks over 70 languages – all using the same model. It’s also worth noting that the emotional and stylistic features (like tags) work across languages, so a [sad] tag or a [whispering] instruction will affect the tone in Spanish or Japanese just as it would in English, adding a layer of expressive consistency globally.
These key features collectively make ElevenLabs v3 a versatile and powerful tool for voice generation. Each one of them is rich enough to warrant deeper exploration – especially audio tags and the dialogue capabilities, which fundamentally change how you interact with the TTS system. In the following sections, we’ll delve into how to use audio tags effectively, how to craft multi-speaker dialogues, and more.
Using Audio Tags: A Deep Dive with Examples
One of the most exciting additions in ElevenLabs v3 is the ability to use audio tags in your text prompts. Audio tags are inline directives you insert in square brackets to control how the AI voice speaks or to trigger non-verbal sounds. Think of them as stage directions for your AI voice actor. This feature gives you an unprecedented level of control over tone, emotion, and even background sounds in the generated speech.
Eleven v3 Examples
5 Videos
How do audio tags work?
It’s simple: include the tag in your script where you want the effect to occur, and the model will interpret it as an audio event rather than spoken words. For example: “I’m not sure this is a good idea [nervous laugh], maybe we should turn back.” In this case, the AI will actually produce a nervous-sounding laugh at the point of the tag, before continuing with the rest of the sentence in voice. These tags do not get spoken aloud; instead, they modify the delivery or insert a sound as specified. Under the hood, ElevenLabs v3 recognizes a variety of tags that can influence the output in different ways. Let’s break down the categories of audio tags and some examples of each:
| Tag Category | Purpose & Examples |
|---|---|
| Emotion & Tone | Conveys the emotional tone or mood of the speech. For example [sad] [angry] [excited] [sarcastic] will make the voice sound sad angry excited or sarcastic respectively. |
| Voice Delivery | Changes the style or manner of speaking. Tags like [whispering] or [whispers] make the voice speak in a whisper [shouting] or [shouts] make it yell and [calm] could induce a steady calm delivery. You can even use [singing] (or [sings]) to have the voice attempt a singing style for a phrase. |
| Non-verbal Sounds | Inserts human reactions or sounds. Examples include [laughs] [laughing] (to chuckle or laugh) [crying] (sobbing or teary voice) [sighs] or [exhales] (a sigh) [clears throat] [giggles] or even [snorts] for a quick snort of laughter. These tags make the voice produce those sounds or speak with the associated nuance (e.g. quivering voice for crying). |
| Sound Effects | Triggers environmental or miscellaneous sound effects beyond the voice itself. You can insert sounds like [applause] (crowd clapping) [gunshot] [explosion] [door creaks] [footsteps] or [telephone rings]. For example: "And the winner is... [drumroll] ... You! [applause]" would include a drumroll sound and then applause. These effects help set scenes and make the audio more immersive. |
| Accents & Special | Applies an accent or other special vocal effect. The tag [strong X accent] lets you specify an accent (replace X with a language or region e.g. [strong French accent] makes the voice speak English with a French accent). Other fun tags include [robotic] (if supported for a monotone robot sound) and some experimental ones like [fart] or [woo] which produce those sounds. These are more experimental/creative tags and may not work uniformly across all voices. |
Note: Categories of audio tags in Eleven v3 and their uses, with example tags. The tags above can be mixed and matched to script very nuanced audio. For instance, if you want a character to laugh while speaking a line, you might do: “[laughing] You really thought I’d fall for that?!” The model will produce a laughing tone intertwined with the speech. If you have a complex emotion to convey, you can even stack tags together – e.g., [angry][laughing] could yield an angry laugh, or [sad][whispers] might make a character speak in a sad, whispering voice. The ElevenLabs team notes that combining multiple tags can result in complex emotional delivery and encourages experimentation to see what combinations work for a given voice.
The Ultimate ElevenLabs Eleven v3 Tag Collection
Take control of your Eleven v3 AI voice generation like never before. This library contains 1450+ meticulously organized Eleven v3 audio tags across 11 categories—from emotional moods and speaking styles to environmental sounds and special effects. Each tag is designed to work seamlessly with ElevenLabs v3, giving you the tools to create truly expressive, human-like voices for any project.
| Eleven v3 Tag | Description | Category |
|---|---|---|
| [calm morning] | Speaker sounds peaceful and serene in the morning | Mood |
| [brisk morning] | Speaker sounds energetic and crisp in the morning | Mood |
| [sleepy morning] | Speaker sounds drowsy and tired in the morning | Mood |
| [groggy morning] | Speaker sounds sluggish and disoriented in the morning | Mood |
| [peaceful morning] | Speaker sounds tranquil and relaxed in the morning | Mood |
| [energetic morning] | Speaker sounds vibrant and full of energy in the morning | Mood |
| [bright morning] | Speaker sounds cheerful and optimistic in the morning | Mood |
| [foggy morning] | Speaker sounds unclear and confused in the morning | Mood |
| [rainy morning] | Speaker sounds melancholic and subdued in the morning | Mood |
| [dewy morning] | Speaker sounds fresh and crisp in the morning | Mood |
| [sunny midday] | Speaker sounds bright and cheerful at midday | Mood |
| [hazy midday] | Speaker sounds unclear and unfocused at midday | Mood |
| [rushed midday] | Speaker sounds hurried and stressed at midday | Mood |
| [reflective midday] | Speaker sounds thoughtful and contemplative at midday | Mood |
| [bored midday] | Speaker sounds uninterested and monotonous at midday | Mood |
| [creative midday] | Speaker sounds inspired and imaginative at midday | Mood |
| [anxious midday] | Speaker sounds worried and tense at midday | Mood |
| [productive midday] | Speaker sounds efficient and accomplished at midday | Mood |
| [hungry midday] | Speaker sounds eager and anticipatory at midday | Mood |
| [restless midday] | Speaker sounds agitated and unsettled at midday | Mood |
| [lazy afternoon] | Speaker sounds relaxed and unhurried in the afternoon | Mood |
| [lethargic afternoon] | Speaker sounds sluggish and low-energy in the afternoon | Mood |
| [motivated afternoon] | Speaker sounds driven and determined in the afternoon | Mood |
| [stressed afternoon] | Speaker sounds tense and overwhelmed in the afternoon | Mood |
| [focused afternoon] | Speaker sounds concentrated and attentive in the afternoon | Mood |
| [daydreaming afternoon] | Speaker sounds distracted and dreamy in the afternoon | Mood |
| [nostalgic afternoon] | Speaker sounds wistful and sentimental in the afternoon | Mood |
| [social afternoon] | Speaker sounds friendly and engaging in the afternoon | Mood |
| [introspective afternoon] | Speaker sounds reflective and self-examining in the afternoon | Mood |
| [energetic afternoon] | Speaker sounds vibrant and lively in the afternoon | Mood |
| [dusk calm] | Speaker sounds peaceful and serene at dusk | Mood |
| [dusk reflective] | Speaker sounds thoughtful and contemplative at dusk | Mood |
| [dusk hopeful] | Speaker sounds optimistic and expectant at dusk | Mood |
| [dusk sad] | Speaker sounds melancholic and sorrowful at dusk | Mood |
| [dusk romantic] | Speaker sounds tender and passionate at dusk | Mood |
| [dusk mysterious] | Speaker sounds enigmatic and intriguing at dusk | Mood |
| [dusk weary] | Speaker sounds tired and exhausted at dusk | Mood |
| [dusk content] | Speaker sounds satisfied and pleased at dusk | Mood |
| [dusk anticipatory] | Speaker sounds expectant and eager at dusk | Mood |
| [dusk meditative] | Speaker sounds calm and spiritual at dusk | Mood |
| [evening relaxed] | Speaker sounds calm and at ease in the evening | Mood |
| [evening upbeat] | Speaker sounds cheerful and positive in the evening | Mood |
| [evening playful] | Speaker sounds fun and lighthearted in the evening | Mood |
| [evening flirtatious] | Speaker sounds charming and teasing in the evening | Mood |
| [evening tired] | Speaker sounds weary and exhausted in the evening | Mood |
| [evening spirited] | Speaker sounds lively and enthusiastic in the evening | Mood |
| [evening mellow] | Speaker sounds smooth and laid-back in the evening | Mood |
| [evening philosophical] | Speaker sounds deep and thoughtful in the evening | Mood |
| [evening melodic] | Speaker sounds musical and rhythmic in the evening | Mood |
| [evening dramatic] | Speaker sounds intense and theatrical in the evening | Mood |
| [night introspective] | Speaker sounds reflective and self-examining at night | Mood |
| [night dreamy] | Speaker sounds ethereal and imaginative at night | Mood |
| [night cautious] | Speaker sounds careful and wary at night | Mood |
| [night fearful] | Speaker sounds scared and anxious at night | Mood |
| [night wistful] | Speaker sounds nostalgic and longing at night | Mood |
| [night creative] | Speaker sounds inspired and artistic at night | Mood |
| [night solitary] | Speaker sounds alone and contemplative at night | Mood |
| [night serene] | Speaker sounds peaceful and tranquil at night | Mood |
| [night anxious] | Speaker sounds worried and restless at night | Mood |
| [night relieved] | Speaker sounds calm and unburdened at night | Mood |
| [late night tired] | Speaker sounds exhausted and weary late at night | Mood |
| [late night determined] | Speaker sounds focused and resolute late at night | Mood |
| [late night nostalgic] | Speaker sounds sentimental and wistful late at night | Mood |
| [late night hopeful] | Speaker sounds optimistic and expectant late at night | Mood |
| [late night gloomy] | Speaker sounds dark and pessimistic late at night | Mood |
| [late night excited] | Speaker sounds energetic and enthusiastic late at night | Mood |
| [early dawn hopeful] | Speaker sounds optimistic and expectant at early dawn | Mood |
| [early dawn quiet] | Speaker sounds peaceful and subdued at early dawn | Mood |
| [early dawn sleepy] | Speaker sounds drowsy and tired at early dawn | Mood |
| [early dawn curious] | Speaker sounds inquisitive and wondering at early dawn | Mood |
| [rush hour tense] | Speaker sounds stressed and agitated during rush hour | Mood |
| [rush hour impatient] | Speaker sounds frustrated and restless during rush hour | Mood |
| [rush hour distracted] | Speaker sounds unfocused and scattered during rush hour | Mood |
| [rush hour annoyed] | Speaker sounds irritated and bothered during rush hour | Mood |
| [rush hour focused] | Speaker sounds concentrated and determined during rush hour | Mood |
| [commute upbeat] | Speaker sounds cheerful and positive during commute | Mood |
| [commute tired] | Speaker sounds weary and exhausted during commute | Mood |
| [commute reflective] | Speaker sounds thoughtful and contemplative during commute | Mood |
| [commute frustrated] | Speaker sounds annoyed and impatient during commute | Mood |
| [commute content] | Speaker sounds satisfied and peaceful during commute | Mood |
| [lunchtime hungry] | Speaker sounds eager and anticipatory at lunchtime | Mood |
| [lunchtime cheerful] | Speaker sounds happy and upbeat at lunchtime | Mood |
| [lunchtime relaxed] | Speaker sounds calm and at ease at lunchtime | Mood |
| [lunchtime rushed] | Speaker sounds hurried and pressed for time at lunchtime | Mood |
| [lunchtime casual] | Speaker sounds laid-back and informal at lunchtime | Mood |
| [midday crisis] | Speaker sounds overwhelmed and stressed during midday crisis | Mood |
| [midday breakthrough] | Speaker sounds triumphant and accomplished during breakthrough | Mood |
| [midday distracted] | Speaker sounds unfocused and scattered at midday | Mood |
| [midday overwhelmed] | Speaker sounds stressed and burdened at midday | Mood |
| [midday relieved] | Speaker sounds calm and unburdened at midday | Mood |
| [workflow focused] | Speaker sounds concentrated and productive in workflow | Mood |
| [workflow productive] | Speaker sounds efficient and accomplished in workflow | Mood |
| [workflow bored] | Speaker sounds uninterested and monotonous in workflow | Mood |
| [workflow challenged] | Speaker sounds engaged and determined in workflow | Mood |
| [workflow creative] | Speaker sounds inspired and innovative in workflow | Mood |
| [deadline pressured] | Speaker sounds stressed and urgent under deadline pressure | Mood |
| [deadline frantic] | Speaker sounds panicked and rushed under deadline pressure | Mood |
| [deadline efficient] | Speaker sounds focused and productive under deadline pressure | Mood |
| [deadline hopeful] | Speaker sounds optimistic and confident under deadline pressure | Mood |
| [deadline stressed] | Speaker sounds tense and overwhelmed under deadline pressure | Mood |
| [post-lunch sleepy] | Speaker sounds drowsy and sluggish after lunch | Mood |
| [post-lunch sluggish] | Speaker sounds slow and lethargic after lunch | Mood |
| [post-lunch regained] | Speaker sounds refreshed and revitalized after lunch | Mood |
| [post-lunch creative] | Speaker sounds inspired and imaginative after lunch | Mood |
| [post-lunch motivated] | Speaker sounds driven and energetic after lunch | Mood |
| [midweek motivational] | Speaker sounds inspiring and encouraging midweek | Mood |
| [midweek tired] | Speaker sounds weary and exhausted midweek | Mood |
| [midweek energetic] | Speaker sounds vibrant and lively midweek | Mood |
| [midweek optimistic] | Speaker sounds positive and hopeful midweek | Mood |
| [midweek reflective] | Speaker sounds thoughtful and contemplative midweek | Mood |
| [weekend relaxed] | Speaker sounds calm and at ease on the weekend | Mood |
| [weekend excited] | Speaker sounds enthusiastic and eager on the weekend | Mood |
| [weekend ambitious] | Speaker sounds driven and goal-oriented on the weekend | Mood |
| [weekend lazy] | Speaker sounds relaxed and unhurried on the weekend | Mood |
| [weekend playful] | Speaker sounds fun and lighthearted on the weekend | Mood |
| [forest morning] | Speaker sounds like they are in a forest during morning | Environment |
| [forest midday] | Speaker sounds like they are in a forest at midday | Environment |
| [forest dusk] | Speaker sounds like they are in a forest at dusk | Environment |
| [forest night] | Speaker sounds like they are in a forest at night | Environment |
| [rainforest ambient] | Speaker sounds like they are in a rainforest environment | Environment |
| [desert daytime] | Speaker sounds like they are in a desert during the day | Environment |
| [desert night] | Speaker sounds like they are in a desert at night | Environment |
| [beach waves] | Speaker sounds like they are near ocean waves at a beach | Environment |
| [beach breeze] | Speaker sounds like they are experiencing a gentle beach breeze | Environment |
| [beach party] | Speaker sounds like they are at a lively beach party | Environment |
| [city street] | Speaker sounds like they are on a busy city street | Environment |
| [city traffic] | Speaker sounds like they are surrounded by city traffic | Environment |
| [city siren] | Speaker sounds like they are hearing emergency sirens in the city | Environment |
| [city subway] | Speaker sounds like they are in an underground subway system | Environment |
| [city crowd] | Speaker sounds like they are in a crowded urban area | Environment |
| [office ambient] | Speaker sounds like they are in a typical office environment | Environment |
| [office typing] | Speaker sounds like they are in an office with typing sounds | Environment |
| [office phone] | Speaker sounds like they are in an office with phone activity | Environment |
| [office chatter] | Speaker sounds like they are in an office with background conversations | Environment |
| [office printer] | Speaker sounds like they are near office equipment like printers | Environment |
| [cafe ambient] | Speaker sounds like they are in a coffee shop atmosphere | Environment |
| [cafe barista] | Speaker sounds like they are near a busy coffee counter | Environment |
| [cafe cups] | Speaker sounds like they are hearing coffee cups and dishes | Environment |
| [cafe conversation] | Speaker sounds like they are in a cafe with conversations | Environment |
| [cafe music] | Speaker sounds like they are in a cafe with background music | Environment |
| [restaurant bustle] | Speaker sounds like they are in a busy restaurant | Environment |
| [restaurant kitchen] | Speaker sounds like they are near a restaurant kitchen | Environment |
| [restaurant cutlery] | Speaker sounds like they are hearing dining utensils | Environment |
| [restaurant waiter] | Speaker sounds like they are interacting with restaurant staff | Environment |
| [restaurant ambient] | Speaker sounds like they are in a restaurant atmosphere | Environment |
| [market ambient] | Speaker sounds like they are in a marketplace environment | Environment |
| [market vendor] | Speaker sounds like they are near market vendors | Environment |
| [market crowd] | Speaker sounds like they are in a crowded market | Environment |
| [market animal] | Speaker sounds like they are in a market with animals | Environment |
| [market chatter] | Speaker sounds like they are hearing market conversations | Environment |
| [rain heavy] | Speaker sounds like they are experiencing heavy rainfall | Environment |
| [rain light] | Speaker sounds like they are experiencing light rain | Environment |
| [thunderstorm] | Speaker sounds like they are in a thunderstorm | Environment |
| [drizzle] | Speaker sounds like they are experiencing drizzling rain | Environment |
| [mist] | Speaker sounds like they are in misty conditions | Environment |
| [wind calm] | Speaker sounds like they are experiencing gentle wind | Environment |
| [wind strong] | Speaker sounds like they are experiencing strong wind | Environment |
| [gusting wind] | Speaker sounds like they are experiencing gusting wind | Environment |
| [leaves rustling] | Speaker sounds like they are hearing leaves in the wind | Environment |
| [tree branches] | Speaker sounds like they are hearing tree branches moving | Environment |
| [river flowing] | Speaker sounds like they are near a flowing river | Environment |
| [waterfall] | Speaker sounds like they are near a waterfall | Environment |
| [stream] | Speaker sounds like they are near a small stream | Environment |
| [ocean waves] | Speaker sounds like they are near ocean waves | Environment |
| [harbor] | Speaker sounds like they are in a harbor environment | Environment |
| [train station] | Speaker sounds like they are in a train station | Environment |
| [train arrival] | Speaker sounds like they are hearing a train arriving | Environment |
| [train departure] | Speaker sounds like they are hearing a train departing | Environment |
| [train rumbling] | Speaker sounds like they are hearing train movement | Environment |
| [train whistle] | Speaker sounds like they are hearing a train whistle | Environment |
| [plane overhead] | Speaker sounds like they are hearing aircraft overhead | Environment |
| [airport ambient] | Speaker sounds like they are in an airport environment | Environment |
| [airport announcement] | Speaker sounds like they are hearing airport announcements | Environment |
| [plane taking off] | Speaker sounds like they are hearing aircraft takeoff | Environment |
| [plane landing] | Speaker sounds like they are hearing aircraft landing | Environment |
| [road trip] | Speaker sounds like they are on a road trip | Environment |
| [car engine] | Speaker sounds like they are hearing car engine sounds | Environment |
| [car horn] | Speaker sounds like they are hearing car horns | Environment |
| [car radio] | Speaker sounds like they are listening to car radio | Environment |
| [car passing] | Speaker sounds like they are hearing cars passing by | Environment |
| [ghostly ambient] | Speaker sounds like they are in a spooky atmosphere | Environment |
| [haunted house] | Speaker sounds like they are in a haunted house | Environment |
| [cellar ambient] | Speaker sounds like they are in a basement or cellar | Environment |
| [attic ambient] | Speaker sounds like they are in an attic space | Environment |
| [abandoned building] | Speaker sounds like they are in an abandoned building | Environment |
| [school classroom] | Speaker sounds like they are in a school classroom | Environment |
| [school bell] | Speaker sounds like they are hearing school bells | Environment |
| [children chatter] | Speaker sounds like they are hearing children talking | Environment |
| [teacher speaking] | Speaker sounds like they are hearing a teacher | Environment |
| [paper shuffling] | Speaker sounds like they are hearing paper being moved | Environment |
| [hospital ambient] | Speaker sounds like they are in a hospital environment | Environment |
| [hospital monitors] | Speaker sounds like they are hearing medical equipment | Environment |
| [hospital announcement] | Speaker sounds like they are hearing hospital announcements | Environment |
| [hospital footsteps] | Speaker sounds like they are hearing footsteps in a hospital | Environment |
| [hospital intercom] | Speaker sounds like they are hearing hospital intercom | Environment |
| [factory hum] | Speaker sounds like they are in a factory with machinery | Environment |
| [factory machinery] | Speaker sounds like they are hearing industrial machinery | Environment |
| [construction] | Speaker sounds like they are at a construction site | Environment |
| [hammering] | Speaker sounds like they are hearing hammering sounds | Environment |
| [drilling] | Speaker sounds like they are hearing drilling sounds | Environment |
| [fuel station ambient] | Speaker sounds like they are at a gas station | Environment |
| [cash register] | Speaker sounds like they are hearing cash register sounds | Environment |
| [supermarket ambient] | Speaker sounds like they are in a supermarket | Environment |
| [shopping cart] | Speaker sounds like they are hearing shopping cart sounds | Environment |
| [checkout beep] | Speaker sounds like they are hearing checkout scanner beeps | Environment |
| [church ambient] | Speaker sounds like they are in a church environment | Environment |
| [church bells] | Speaker sounds like they are hearing church bells | Environment |
| [choir] | Speaker sounds like they are hearing choir singing | Environment |
| [prayer] | Speaker sounds like they are in a prayer atmosphere | Environment |
| [sermon] | Speaker sounds like they are hearing a sermon | Environment |
| [stadium crowd] | Speaker sounds like they are in a stadium with crowd noise | Environment |
| [stadium cheer] | Speaker sounds like they are hearing stadium cheering | Environment |
| [stadium announcer] | Speaker sounds like they are hearing stadium announcements | Environment |
| [stadium whistle] | Speaker sounds like they are hearing sports whistles | Environment |
| [stadium team chant] | Speaker sounds like they are hearing team chants | Environment |
| [concert ambient] | Speaker sounds like they are at a concert venue | Environment |
| [audience applause] | Speaker sounds like they are hearing audience applause | Environment |
| [concert guitar] | Speaker sounds like they are hearing live guitar music | Environment |
| [concert drums] | Speaker sounds like they are hearing live drum music | Environment |
| [concert singer] | Speaker sounds like they are hearing live vocal performance | Environment |
| [campfire crackle] | Speaker sounds like they are near a crackling campfire | Environment |
| [campfire storytelling] | Speaker sounds like they are at campfire storytelling | Environment |
| [campground ambient] | Speaker sounds like they are in a campground environment | Environment |
| [wildlife night] | Speaker sounds like they are hearing nighttime wildlife | Environment |
| [owl hoot] | Speaker sounds like they are hearing owl sounds | Environment |
| [library ambient] | Speaker sounds like they are in a quiet library | Environment |
| [page flipping] | Speaker sounds like they are hearing pages turning | Environment |
| [quiet whisper] | Speaker sounds like they are in a very quiet environment | Environment |
| [footsteps hallway] | Speaker sounds like they are hearing hallway footsteps | Environment |
| [security alarm] | Speaker sounds like they are hearing security alarms | Environment |
| [zen garden] | Speaker sounds like they are in a peaceful zen garden | Environment |
| [meditation chant] | Speaker sounds like they are hearing meditation chanting | Environment |
| [fountain ambient] | Speaker sounds like they are near a water fountain | Environment |
| [garden birds] | Speaker sounds like they are hearing birds in a garden | Environment |
| [wind chimes] | Speaker sounds like they are hearing wind chimes | Environment |
| [breathing heavily] | Speaker sounds like they are breathing heavily | Body States |
| [short of breath] | Speaker sounds like they are having difficulty breathing | Body States |
| [coughing lightly] | Speaker sounds like they are coughing softly | Body States |
| [wheezing softly] | Speaker sounds like they have slight breathing difficulty | Body States |
| [sniffling] | Speaker sounds like they are sniffling | Body States |
| [shivering] | Speaker sounds like they are cold and shivering | Body States |
| [trembling] | Speaker sounds like they are trembling or shaking | Body States |
| [sweating] | Speaker sounds like they are perspiring | Body States |
| [panting] | Speaker sounds like they are breathing rapidly | Body States |
| [heart racing] | Speaker sounds like their heart is beating fast | Body States |
| [heart pounding] | Speaker sounds like their heart is beating strongly | Body States |
| [dizzy] | Speaker sounds like they are feeling dizzy | Body States |
| [lightheaded] | Speaker sounds like they feel faint | Body States |
| [faint] | Speaker sounds like they are about to faint | Body States |
| [staggering] | Speaker sounds like they are walking unsteadily | Body States |
| [limping] | Speaker sounds like they are walking with a limp | Body States |
| [hunched] | Speaker sounds like they are in a hunched posture | Body States |
| [stretching] | Speaker sounds like they are stretching their body | Body States |
| [cracking joints] | Speaker sounds like they are cracking their joints | Body States |
| [aching] | Speaker sounds like they are in pain | Body States |
| [sore throat] | Speaker sounds like they have a sore throat | Body States |
| [tight chest] | Speaker sounds like they have chest tightness | Body States |
| [stomach gurgling] | Speaker sounds like their stomach is making noise | Body States |
| [hungry grumbling] | Speaker sounds like their stomach is grumbling from hunger | Body States |
| [full belly] | Speaker sounds like they are full from eating | Body States |
| [burping] | Speaker sounds like they are burping | Body States |
| [hiccuping] | Speaker sounds like they have hiccups | Body States |
| [belly ache] | Speaker sounds like they have stomach pain | Body States |
| [vomiting] | Speaker sounds like they are vomiting | Body States |
| [dry mouth] | Speaker sounds like they have a dry mouth | Body States |
| [thirsty] | Speaker sounds like they are thirsty | Body States |
| [yawning] | Speaker sounds like they are yawning | Body States |
| [restless] | Speaker sounds like they are restless | Body States |
| [jittery] | Speaker sounds like they are nervous and jittery | Body States |
| [fidgeting] | Speaker sounds like they are fidgeting | Body States |
| [sweat dripping] | Speaker sounds like sweat is dripping | Body States |
| [clammy skin] | Speaker sounds like they have clammy skin | Body States |
| [cold skin] | Speaker sounds like they have cold skin | Body States |
| [tingling] | Speaker sounds like they feel tingling sensations | Body States |
| [numb] | Speaker sounds like they feel numbness | Body States |
| [headache] | Speaker sounds like they have a headache | Body States |
| [throbbing] | Speaker sounds like they feel throbbing pain | Body States |
| [sharp pain] | Speaker sounds like they feel sharp pain | Body States |
| [stiff neck] | Speaker sounds like they have a stiff neck | Body States |
| [sore muscles] | Speaker sounds like they have sore muscles | Body States |
| [cramps] | Speaker sounds like they have muscle cramps | Body States |
| [muscle twitch] | Speaker sounds like they have muscle twitches | Body States |
| [back pain] | Speaker sounds like they have back pain | Body States |
| [stiff joints] | Speaker sounds like they have stiff joints | Body States |
| [blurry vision] | Speaker sounds like they have blurry vision | Body States |
| [burning eyes] | Speaker sounds like their eyes are burning | Body States |
| [itching] | Speaker sounds like they are itching | Body States |
| [sneezing] | Speaker sounds like they are sneezing | Body States |
| [runny nose] | Speaker sounds like they have a runny nose | Body States |
| [block nose] | Speaker sounds like they have a blocked nose | Body States |
| [ear ringing] | Speaker sounds like they have ringing in their ears | Body States |
| [ear popping] | Speaker sounds like their ears are popping | Body States |
| [taste bitter] | Speaker sounds like they taste something bitter | Body States |
| [taste sweet] | Speaker sounds like they taste something sweet | Body States |
| [taste sour] | Speaker sounds like they taste something sour | Body States |
| [taste metallic] | Speaker sounds like they taste something metallic | Body States |
| [dry skin] | Speaker sounds like they have dry skin | Body States |
| [flushed] | Speaker sounds like they are flushed | Body States |
| [pale] | Speaker sounds like they are pale | Body States |
| [blushing] | Speaker sounds like they are blushing | Body States |
| [goosebumps] | Speaker sounds like they have goosebumps | Body States |
| [hair standing] | Speaker sounds like their hair is standing up | Body States |
| [sunburned] | Speaker sounds like they are sunburned | Body States |
| [cold shiver] | Speaker sounds like they are shivering from cold | Body States |
| [heat wave] | Speaker sounds like they are experiencing heat | Body States |
| [cramp stomach] | Speaker sounds like they have stomach cramps | Body States |
| [stomach rumble] | Speaker sounds like their stomach is rumbling | Body States |
| [gas pain] | Speaker sounds like they have gas pain | Body States |
| [crunch stepping] | Speaker sounds like they are stepping on something crunchy | Body States |
| [foot ache] | Speaker sounds like their feet are aching | Body States |
| [pinch] | Speaker sounds like they feel a pinching sensation | Body States |
| [sore foot] | Speaker sounds like they have sore feet | Body States |
| [nail tapping] | Speaker sounds like they are tapping their nails | Body States |
| [knuckles cracking] | Speaker sounds like they are cracking their knuckles | Body States |
| [jaw clench] | Speaker sounds like they are clenching their jaw | Body States |
| [teeth grinding] | Speaker sounds like they are grinding their teeth | Body States |
| [lip biting] | Speaker sounds like they are biting their lips | Body States |
| [mouth dry] | Speaker sounds like they have a dry mouth | Body States |
| [mouth watery] | Speaker sounds like their mouth is watery | Body States |
| [swallow saliva] | Speaker sounds like they are swallowing saliva | Body States |
| [stomach crunch] | Speaker sounds like their stomach is crunching | Body States |
| [belly sigh] | Speaker sounds like they are sighing from their belly | Body States |
| [stomach groan] | Speaker sounds like their stomach is groaning | Body States |
| [knee knock] | Speaker sounds like their knees are knocking | Body States |
| [shin pain] | Speaker sounds like they have shin pain | Body States |
| [aching knee] | Speaker sounds like their knees are aching | Body States |
| [thigh burn] | Speaker sounds like their thighs are burning | Body States |
| [calf ache] | Speaker sounds like their calves are aching | Body States |
| [shoulder ache] | Speaker sounds like their shoulders are aching | Body States |
| [neck crack] | Speaker sounds like their neck is cracking | Body States |
| [head tilt] | Speaker sounds like they are tilting their head | Body States |
| [eye blink] | Speaker sounds like they are blinking | Body States |
| [eye roll] | Speaker sounds like they are rolling their eyes | Body States |
| [lift heavy] | Speaker sounds like they are lifting something heavy | Body States |
| [push heavy] | Speaker sounds like they are pushing something heavy | Body States |
| [stretch arms] | Speaker sounds like they are stretching their arms | Body States |
| [stretch back] | Speaker sounds like they are stretching their back | Body States |
| [sit slowly] | Speaker sounds like they are sitting down slowly | Body States |
| [stand slowly] | Speaker sounds like they are standing up slowly | Body States |
| [walk softly] | Speaker sounds like they are walking softly | Body States |
| [run softly] | Speaker sounds like they are running softly | Body States |
| [crawl] | Speaker sounds like they are crawling | Body States |
| [limp slowly] | Speaker sounds like they are limping slowly | Body States |
| [wake up stretch] | Speaker sounds like they are stretching after waking up | Body States |
| [yawn stretch] | Speaker sounds like they are yawning and stretching | Body States |
| [sleep rustle] | Speaker sounds like they are rustling in their sleep | Body States |
| [blank stare] | Speaker sounds like they are staring blankly | Body States |
| [focused glance] | Speaker sounds like they are glancing with focus | Body States |
| [dramatic pause] | Speaker uses dramatic pauses for effect | Narrative |
| [narrative flourish] | Speaker adds elaborate narrative embellishments | Narrative |
| [storytelling tone] | Speaker uses a classic storytelling voice | Narrative |
| [voice-over style] | Speaker sounds like a voice-over narrator | Narrative |
| [cinematic tone] | Speaker uses a movie-like narrative style | Narrative |
| [documentary style] | Speaker sounds like a documentary narrator | Narrative |
| [informative style] | Speaker uses an educational narrative tone | Narrative |
| [conversational tone] | Speaker uses a casual, conversational narrative | Narrative |
| [reflective tone] | Speaker uses a thoughtful, reflective narrative | Narrative |
| [philosophical tone] | Speaker uses a deep, philosophical narrative | Narrative |
| [dramatic reveal] | Speaker builds up to dramatic revelations | Narrative |
| [suspense build-up] | Speaker creates suspenseful narrative tension | Narrative |
| [cliffhanger] | Speaker ends with suspenseful cliffhangers | Narrative |
| [narrator aside] | Speaker makes narrative asides to the audience | Narrative |
| [omniscient narrator] | Speaker uses an all-knowing narrative perspective | Narrative |
| [first-person narrative] | Speaker tells story from first-person perspective | Narrative |
| [third-person narrative] | Speaker tells story from third-person perspective | Narrative |
| [unreliable narrator] | Speaker uses an unreliable narrative voice | Narrative |
| [stream of consciousness] | Speaker uses flowing, unstructured narrative | Narrative |
| [flashback tone] | Speaker narrates flashback sequences | Narrative |
| [flashforward tone] | Speaker narrates future events | Narrative |
| [inner monologue] | Speaker voices internal thoughts | Narrative |
| [prose reading] | Speaker reads with literary prose style | Narrative |
| [poetic reading] | Speaker uses poetic narrative rhythm | Narrative |
| [epic saga tone] | Speaker uses grand, epic narrative style | Narrative |
| [mythic tone] | Speaker uses legendary, mythical narrative | Narrative |
| [fairytale style] | Speaker uses classic fairytale narrative | Narrative |
| [fable style] | Speaker uses moral fable narrative tone | Narrative |
| [legendary tone] | Speaker uses heroic legend narrative | Narrative |
| [historical recount] | Speaker narrates historical events | Narrative |
| [memoir tone] | Speaker uses personal memoir style | Narrative |
| [journal entry tone] | Speaker sounds like reading a diary | Narrative |
| [letter reading] | Speaker sounds like reading correspondence | Narrative |
| [interview style] | Speaker uses interview narrative format | Narrative |
| [analytical tone] | Speaker uses analytical narrative approach | Narrative |
| [scientific tone] | Speaker uses scientific narrative style | Narrative |
| [educational tone] | Speaker uses teaching narrative tone | Narrative |
| [instructional tone] | Speaker uses how-to narrative style | Narrative |
| [motivational tone] | Speaker uses inspiring narrative voice | Narrative |
| [coach voice] | Speaker uses coaching narrative style | Narrative |
| [mentor voice] | Speaker uses mentoring narrative tone | Narrative |
| [warning tone] | Speaker uses cautionary narrative voice | Narrative |
| [advice tone] | Speaker uses advisory narrative style | Narrative |
| [cautionary tone] | Speaker uses warning narrative approach | Narrative |
| [legal tone] | Speaker uses formal legal narrative | Narrative |
| [reporter style] | Speaker uses news reporter narrative | Narrative |
| [news anchor tone] | Speaker uses broadcast news narrative | Narrative |
| [weather reporter tone] | Speaker uses weather forecast narrative | Narrative |
| [sports announcer] | Speaker uses sports commentary narrative | Narrative |
| [play-by-play style] | Speaker uses live sports narrative | Narrative |
| [studio announcer] | Speaker uses studio announcement style | Narrative |
| [podcast host] | Speaker uses podcast hosting narrative | Narrative |
| [vlog style] | Speaker uses video blog narrative tone | Narrative |
| [casual chat] | Speaker uses informal chat narrative | Narrative |
| [energetic narration] | Speaker uses high-energy narrative style | Narrative |
| [soothing narration] | Speaker uses calming narrative tone | Narrative |
| [meditative reading] | Speaker uses peaceful, meditative narrative | Narrative |
| [storybook style] | Speaker uses children's storybook narrative | Narrative |
| [kids story tone] | Speaker uses child-friendly narrative | Narrative |
| [adult story tone] | Speaker uses mature narrative style | Narrative |
| [bedtime story] | Speaker uses sleepy bedtime narrative | Narrative |
| [campfire storytelling] | Speaker uses outdoor storytelling style | Narrative |
| [urban legend tone] | Speaker uses mysterious urban legend narrative | Narrative |
| [detective story tone] | Speaker uses mystery detective narrative | Narrative |
| [noir narration] | Speaker uses dark, noir narrative style | Narrative |
| [crime thriller tone] | Speaker uses suspenseful crime narrative | Narrative |
| [horror narration] | Speaker uses scary horror narrative | Narrative |
| [ghost story tone] | Speaker uses spooky ghost story narrative | Narrative |
| [comedy narration] | Speaker uses humorous narrative style | Narrative |
| [satirical narration] | Speaker uses satirical narrative tone | Narrative |
| [ironical tone] | Speaker uses ironic narrative approach | Narrative |
| [deadpan narration] | Speaker uses flat, emotionless narrative | Narrative |
| [sarcastic narration] | Speaker uses sarcastic narrative tone | Narrative |
| [parodic tone] | Speaker uses parody narrative style | Narrative |
| [whimsical style] | Speaker uses playful, whimsical narrative | Narrative |
| [quirky tone] | Speaker uses eccentric narrative style | Narrative |
| [absurdist narration] | Speaker uses absurd narrative approach | Narrative |
| [avant-garde tone] | Speaker uses experimental narrative style | Narrative |
| [experimental narrative] | Speaker uses unconventional narrative | Narrative |
| [found footage style] | Speaker uses discovered recording narrative | Narrative |
| [mockumentary tone] | Speaker uses fake documentary narrative | Narrative |
| [confessional tone] | Speaker uses personal confession narrative | Narrative |
| [testimonial style] | Speaker uses witness testimony narrative | Narrative |
| [oral history style] | Speaker uses spoken history narrative | Narrative |
| [poetic imagery] | Speaker uses vivid poetic narrative | Narrative |
| [vivid description] | Speaker uses detailed descriptive narrative | Narrative |
| [sensory detail] | Speaker uses sensory-rich narrative | Narrative |
| [minimalist narration] | Speaker uses sparse, minimal narrative | Narrative |
| [maximalist narration] | Speaker uses elaborate, detailed narrative | Narrative |
| [slow reveal] | Speaker gradually reveals information | Narrative |
| [fast-paced narration] | Speaker uses rapid narrative pace | Narrative |
| [pauses for effect] | Speaker uses strategic pauses in narrative | Narrative |
| [understated tone] | Speaker uses subtle, understated narrative | Narrative |
| [over-the-top narration] | Speaker uses exaggerated narrative style | Narrative |
| [epic build-up] | Speaker builds to epic climax | Narrative |
| [crescendo tone] | Speaker builds narrative intensity | Narrative |
| [anticlimactic reveal] | Speaker deflates narrative tension | Narrative |
| [tense narration] | Speaker uses suspenseful narrative tension | Narrative |
| [calming narration] | Speaker uses peaceful narrative tone | Narrative |
| [uplifting narration] | Speaker uses inspiring narrative style | Narrative |
| [melancholic narration] | Speaker uses sad, wistful narrative | Narrative |
| [romantic narration] | Speaker uses romantic narrative tone | Narrative |
| [tragic narration] | Speaker uses sorrowful narrative style | Narrative |
| [humorous narration] | Speaker uses funny narrative approach | Narrative |
| [dead serious narration] | Speaker uses completely serious narrative | Narrative |
| [mock heroic tone] | Speaker uses exaggerated heroic narrative | Narrative |
| [tragicomedy tone] | Speaker mixes tragic and comic narrative | Narrative |
| [Satire voice] | Speaker uses satirical narrative voice | Narrative |
| [moralizing tone] | Speaker uses preachy narrative style | Narrative |
| [inspiring tone] | Speaker uses motivational narrative | Narrative |
| [hopeful narration] | Speaker uses optimistic narrative tone | Narrative |
| [doubtful narration] | Speaker uses uncertain narrative voice | Narrative |
| [skeptical narration] | Speaker uses questioning narrative tone | Narrative |
| [wonder-filled narration] | Speaker uses amazed narrative style | Narrative |
| [childlike narration] | Speaker uses innocent narrative voice | Narrative |
| [child narrator] | Speaker sounds like a child telling story | Narrative |
| [dramatic irony] | Speaker uses dramatic irony in narrative | Narrative |
| [foreshadowing tone] | Speaker hints at future events | Narrative |
| [callback narration] | Speaker references earlier narrative points | Narrative |
| [refrain voice] | Speaker repeats narrative elements | Narrative |
| [fantasy] | Speaker sounds like they are in a fantasy setting | Genre |
| [high fantasy] | Speaker sounds like they are in an epic fantasy world | Genre |
| [dark fantasy] | Speaker sounds like they are in a dark fantasy setting | Genre |
| [urban fantasy] | Speaker sounds like they are in a modern fantasy world | Genre |
| [epic fantasy] | Speaker sounds like they are in a grand fantasy adventure | Genre |
| [mythic fantasy] | Speaker sounds like they are in a mythological fantasy | Genre |
| [sword and sorcery] | Speaker sounds like they are in a sword and sorcery tale | Genre |
| [fairy tale] | Speaker sounds like they are in a fairy tale story | Genre |
| [fable] | Speaker sounds like they are telling a moral fable | Genre |
| [legend] | Speaker sounds like they are recounting a legend | Genre |
| [steampunk] | Speaker sounds like they are in a steampunk world | Genre |
| [dieselpunk] | Speaker sounds like they are in a dieselpunk setting | Genre |
| [cyberpunk] | Speaker sounds like they are in a cyberpunk future | Genre |
| [biopunk] | Speaker sounds like they are in a biopunk world | Genre |
| [dystopian] | Speaker sounds like they are in a dystopian society | Genre |
| [post-apocalyptic] | Speaker sounds like they are in a post-apocalyptic world | Genre |
| [sci-fi] | Speaker sounds like they are in a science fiction setting | Genre |
| [space opera] | Speaker sounds like they are in an epic space adventure | Genre |
| [hard sci-fi] | Speaker sounds like they are in a realistic sci-fi world | Genre |
| [soft sci-fi] | Speaker sounds like they are in a speculative sci-fi setting | Genre |
| [alien encounter] | Speaker sounds like they are encountering aliens | Genre |
| [first contact] | Speaker sounds like they are making first alien contact | Genre |
| [time travel] | Speaker sounds like they are involved in time travel | Genre |
| [parallel universe] | Speaker sounds like they are in an alternate reality | Genre |
| [alternate history] | Speaker sounds like they are in an alternate timeline | Genre |
| [detective] | Speaker sounds like they are in a detective story | Genre |
| [noir] | Speaker sounds like they are in a film noir setting | Genre |
| [hard-boiled] | Speaker sounds like they are in a hard-boiled detective story | Genre |
| [crime thriller] | Speaker sounds like they are in a crime thriller | Genre |
| [legal thriller] | Speaker sounds like they are in a legal thriller | Genre |
| [political thriller] | Speaker sounds like they are in a political thriller | Genre |
| [psychological thriller] | Speaker sounds like they are in a psychological thriller | Genre |
| [supernatural horror] | Speaker sounds like they are in a supernatural horror | Genre |
| [cosmic horror] | Speaker sounds like they are in a cosmic horror story | Genre |
| [gothic horror] | Speaker sounds like they are in a gothic horror setting | Genre |
| [slasher] | Speaker sounds like they are in a slasher horror story | Genre |
| [zombie apocalypse] | Speaker sounds like they are in a zombie apocalypse | Genre |
| [monster story] | Speaker sounds like they are in a monster story | Genre |
| [urban horror] | Speaker sounds like they are in an urban horror setting | Genre |
| [body horror] | Speaker sounds like they are in a body horror story | Genre |
| [comedy] | Speaker sounds like they are in a comedy | Genre |
| [romantic comedy] | Speaker sounds like they are in a romantic comedy | Genre |
| [satire] | Speaker sounds like they are in a satirical story | Genre |
| [parody] | Speaker sounds like they are in a parody | Genre |
| [slapstick] | Speaker sounds like they are in a slapstick comedy | Genre |
| [absurdist] | Speaker sounds like they are in an absurdist story | Genre |
| [dark comedy] | Speaker sounds like they are in a dark comedy | Genre |
| [camp] | Speaker sounds like they are in a campy story | Genre |
| [campy horror] | Speaker sounds like they are in a campy horror story | Genre |
| [mockumentary] | Speaker sounds like they are in a mockumentary | Genre |
| [drama] | Speaker sounds like they are in a dramatic story | Genre |
| [historical drama] | Speaker sounds like they are in a historical drama | Genre |
| [family drama] | Speaker sounds like they are in a family drama | Genre |
| [coming-of-age drama] | Speaker sounds like they are in a coming-of-age story | Genre |
| [musical] | Speaker sounds like they are in a musical | Genre |
| [rock musical] | Speaker sounds like they are in a rock musical | Genre |
| [opera] | Speaker sounds like they are in an opera | Genre |
| [jazz musical] | Speaker sounds like they are in a jazz musical | Genre |
| [electro musical] | Speaker sounds like they are in an electronic musical | Genre |
| [mystery] | Speaker sounds like they are in a mystery story | Genre |
| [cozy mystery] | Speaker sounds like they are in a cozy mystery | Genre |
| [whodunit] | Speaker sounds like they are in a whodunit mystery | Genre |
| [puzzle mystery] | Speaker sounds like they are in a puzzle mystery | Genre |
| [locked room] | Speaker sounds like they are in a locked room mystery | Genre |
| [adventure] | Speaker sounds like they are on an adventure | Genre |
| [swashbuckling] | Speaker sounds like they are in a swashbuckling adventure | Genre |
| [quest] | Speaker sounds like they are on a quest | Genre |
| [epic journey] | Speaker sounds like they are on an epic journey | Genre |
| [exploration] | Speaker sounds like they are exploring unknown territory | Genre |
| [survival] | Speaker sounds like they are in a survival story | Genre |
| [war epic] | Speaker sounds like they are in a war epic | Genre |
| [military sci-fi] | Speaker sounds like they are in military science fiction | Genre |
| [spy thriller] | Speaker sounds like they are in a spy thriller | Genre |
| [espionage] | Speaker sounds like they are in an espionage story | Genre |
| [political drama] | Speaker sounds like they are in a political drama | Genre |
| [courtroom drama] | Speaker sounds like they are in a courtroom drama | Genre |
| [legal drama] | Speaker sounds like they are in a legal drama | Genre |
| [sports drama] | Speaker sounds like they are in a sports drama | Genre |
| [western] | Speaker sounds like they are in a western | Genre |
| [spaghetti western] | Speaker sounds like they are in a spaghetti western | Genre |
| [revisionist western] | Speaker sounds like they are in a revisionist western | Genre |
| [space western] | Speaker sounds like they are in a space western | Genre |
| [family-friendly fantasy] | Speaker sounds like they are in family-friendly fantasy | Genre |
| [children's adventure] | Speaker sounds like they are in a children's adventure | Genre |
| [young adult] | Speaker sounds like they are in a young adult story | Genre |
| [superhero] | Speaker sounds like they are in a superhero story | Genre |
| [vigilante] | Speaker sounds like they are in a vigilante story | Genre |
| [antihero] | Speaker sounds like they are in an antihero story | Genre |
| [whimsical] | Speaker sounds like they are in a whimsical story | Genre |
| [magical realism] | Speaker sounds like they are in magical realism | Genre |
| [urban drama] | Speaker sounds like they are in an urban drama | Genre |
| [slice of life] | Speaker sounds like they are in a slice of life story | Genre |
| [bildungsroman] | Speaker sounds like they are in a coming-of-age novel | Genre |
| [road trip] | Speaker sounds like they are on a road trip story | Genre |
| [ghost story] | Speaker sounds like they are in a ghost story | Genre |
| [paranormal] | Speaker sounds like they are in a paranormal story | Genre |
| [occult] | Speaker sounds like they are in an occult story | Genre |
| [witch tale] | Speaker sounds like they are in a witch story | Genre |
| [vampire story] | Speaker sounds like they are in a vampire story | Genre |
| [werewolf story] | Speaker sounds like they are in a werewolf story | Genre |
| [pirate adventure] | Speaker sounds like they are in a pirate adventure | Genre |
| [sea voyage] | Speaker sounds like they are on a sea voyage | Genre |
| [nautical] | Speaker sounds like they are in a nautical story | Genre |
| [medieval] | Speaker sounds like they are in a medieval setting | Genre |
| [renaissance] | Speaker sounds like they are in a renaissance setting | Genre |
| [victorian] | Speaker sounds like they are in a victorian setting | Genre |
| [steampunk detective] | Speaker sounds like they are in a steampunk detective story | Genre |
| [robot uprising] | Speaker sounds like they are in a robot uprising story | Genre |
| [AI rebellion] | Speaker sounds like they are in an AI rebellion story | Genre |
| [cyber-thriller] | Speaker sounds like they are in a cyber-thriller | Genre |
| [eco-thriller] | Speaker sounds like they are in an eco-thriller | Genre |
| [interrupts] | Speaker interrupts another speaker | Dialogue |
| [overlapping speech] | Speaker talks at the same time as others | Dialogue |
| [cuts in] | Speaker cuts into the conversation | Dialogue |
| [talks over] | Speaker talks over another person | Dialogue |
| [pitch rises] | Speaker's voice pitch rises during dialogue | Dialogue |
| [pause mid-sentence] | Speaker pauses in the middle of speaking | Dialogue |
| [hesitates] | Speaker hesitates while speaking | Dialogue |
| [clarifying tone] | Speaker uses a tone to clarify something | Dialogue |
| [confirming tone] | Speaker uses a tone to confirm something | Dialogue |
| [questioning tone] | Speaker uses an inquisitive tone | Dialogue |
| [responds quickly] | Speaker responds rapidly to dialogue | Dialogue |
| [responds slowly] | Speaker responds slowly to dialogue | Dialogue |
| [asks politely] | Speaker asks questions politely | Dialogue |
| [asks bluntly] | Speaker asks questions directly and bluntly | Dialogue |
| [repeats question] | Speaker repeats their question | Dialogue |
| [echoes statement] | Speaker echoes what was said | Dialogue |
| [reframes] | Speaker reframes the conversation | Dialogue |
| [summarizes] | Speaker summarizes what was discussed | Dialogue |
| [paraphrases] | Speaker rephrases what was said | Dialogue |
| [inquires] | Speaker makes an inquiry | Dialogue |
| [proposes] | Speaker proposes something in dialogue | Dialogue |
| [suggests] | Speaker makes a suggestion | Dialogue |
| [urges] | Speaker urges someone to do something | Dialogue |
| [insists] | Speaker insists on something | Dialogue |
| [demands] | Speaker demands something | Dialogue |
| [negotiates] | Speaker negotiates in the conversation | Dialogue |
| [bargains] | Speaker bargains during dialogue | Dialogue |
| [apologizes mid-sentence] | Speaker apologizes while speaking | Dialogue |
| [corrects self] | Speaker corrects themselves while speaking | Dialogue |
| [self-interrupt] | Speaker interrupts themselves | Dialogue |
| [presses pause] | Speaker pauses to emphasize | Dialogue |
| [sighs between lines] | Speaker sighs between dialogue lines | Dialogue |
| [laughs interrupting] | Speaker laughs while interrupting | Dialogue |
| [soft rebuttal] | Speaker gently rebuts something | Dialogue |
| [sharp rebuttal] | Speaker sharply rebuts something | Dialogue |
| [soft affirmation] | Speaker gently affirms something | Dialogue |
| [firm affirmation] | Speaker firmly affirms something | Dialogue |
| [soft negation] | Speaker gently denies something | Dialogue |
| [firm negation] | Speaker firmly denies something | Dialogue |
| [reluctant agreement] | Speaker reluctantly agrees | Dialogue |
| [eager agreement] | Speaker eagerly agrees | Dialogue |
| [reluctant refusal] | Speaker reluctantly refuses | Dialogue |
| [eager refusal] | Speaker eagerly refuses | Dialogue |
| [changes subject] | Speaker changes the topic | Dialogue |
| [redirects] | Speaker redirects the conversation | Dialogue |
| [interruptive gasp] | Speaker gasps while interrupting | Dialogue |
| [interruptive cough] | Speaker coughs while interrupting | Dialogue |
| [stammered apology] | Speaker stammers while apologizing | Dialogue |
| [closes loop] | Speaker brings the conversation full circle | Dialogue |
| [opens loop] | Speaker starts a new conversation thread | Dialogue |
| [building tension] | Speaker builds tension in dialogue | Dialogue |
| [diffusing tension] | Speaker reduces tension in dialogue | Dialogue |
| [rising clarity] | Speaker becomes clearer as they speak | Dialogue |
| [falling clarity] | Speaker becomes less clear as they speak | Dialogue |
| [building anticipation] | Speaker builds anticipation in dialogue | Dialogue |
| [releasing anticipation] | Speaker releases built-up anticipation | Dialogue |
| [mock surprise] | Speaker feigns surprise in dialogue | Dialogue |
| [real surprise] | Speaker expresses genuine surprise | Dialogue |
| [soft whisper to respond] | Speaker whispers their response | Dialogue |
| [shouted reply] | Speaker shouts their reply | Dialogue |
| [sotto voce response] | Speaker responds in an undertone | Dialogue |
| [dialogue crescendo] | Speaker builds intensity in dialogue | Dialogue |
| [dialogue decrescendo] | Speaker decreases intensity in dialogue | Dialogue |
| [echo reply] | Speaker's reply echoes what was said | Dialogue |
| [dialogue tag aside] | Speaker makes an aside comment | Dialogue |
| [parenthetical aside] | Speaker makes a parenthetical comment | Dialogue |
| [metadialogue] | Speaker comments on the dialogue itself | Dialogue |
| [narrator interrupts] | Narrator interrupts the dialogue | Dialogue |
| [sidekick interrupts] | Supporting character interrupts | Dialogue |
| [foil interrupts] | Opposing character interrupts | Dialogue |
| [comic relief interjection] | Comic character makes an interjection | Dialogue |
| [dramatic interjection] | Speaker makes a dramatic interjection | Dialogue |
| [exasperated interjection] | Speaker makes an exasperated interjection | Dialogue |
| [gentle interjection] | Speaker makes a gentle interjection | Dialogue |
| [harsh interjection] | Speaker makes a harsh interjection | Dialogue |
| [humorous interruption] | Speaker interrupts with humor | Dialogue |
| [serious interruption] | Speaker interrupts seriously | Dialogue |
| [emotional outburst] | Speaker has an emotional outburst | Dialogue |
| [controlled outburst] | Speaker has a controlled outburst | Dialogue |
| [laughter break] | Speaker breaks into laughter | Dialogue |
| [sob break] | Speaker breaks into sobbing | Dialogue |
| [chuckle break] | Speaker breaks into chuckling | Dialogue |
| [back and forth] | Speaker engages in rapid dialogue exchange | Dialogue |
| [rapid exchange] | Speaker engages in quick dialogue | Dialogue |
| [slow exchange] | Speaker engages in slow dialogue | Dialogue |
| [echoing question] | Speaker echoes a question | Dialogue |
| [repeated echo] | Speaker repeats an echo | Dialogue |
| [rising echo] | Speaker's echo rises in intensity | Dialogue |
| [falling echo] | Speaker's echo falls in intensity | Dialogue |
| [dialogue harmonizing] | Speakers harmonize in dialogue | Dialogue |
| [dialogue dissonance] | Speakers create dissonance in dialogue | Dialogue |
| [conversational overlap] | Multiple speakers overlap naturally | Dialogue |
| [interrupted thought] | Speaker's thought gets interrupted | Dialogue |
| [dialogue reflection] | Speaker reflects on the dialogue | Dialogue |
| [reflective response] | Speaker gives a reflective response | Dialogue |
| [dialogue summary] | Speaker summarizes the dialogue | Dialogue |
| [dialogue follow‑up] | Speaker follows up on dialogue | Dialogue |
| [clarifying pause] | Speaker pauses to clarify | Dialogue |
| [reflective pause] | Speaker pauses to reflect | Dialogue |
| [tension pause] | Speaker pauses creating tension | Dialogue |
| [relief pause] | Speaker pauses with relief | Dialogue |
| [anticipatory pause] | Speaker pauses with anticipation | Dialogue |
| [pregnant pause] | Speaker makes a meaningful pause | Dialogue |
| [beat change] | Speaker changes the dialogue beat | Dialogue |
| [tone shift] | Speaker shifts their tone | Dialogue |
| [mood match] | Speaker matches the mood | Dialogue |
| [mood clash] | Speaker clashes with the mood | Dialogue |
| [dialogue tag whisper] | Speaker whispers dialogue tags | Dialogue |
| [dialogue tag shout] | Speaker shouts dialogue tags | Dialogue |
| [dialogue tag sigh] | Speaker sighs dialogue tags | Dialogue |
| [dialogue tag laugh] | Speaker laughs dialogue tags | Dialogue |
| [dialogue tag gasp] | Speaker gasps dialogue tags | Dialogue |
| [robotic modulation] | Speaker sounds like robotic voice modulation | Effects |
| [glitch] | Speaker sounds like digital glitch effect | Effects |
| [vocoder] | Speaker sounds like vocoder effect | Effects |
| [electric hum] | Speaker sounds like electric humming effect | Effects |
| [digital distortion] | Speaker sounds like digital distortion effect | Effects |
| [bitcrushed] | Speaker sounds like bitcrushed audio effect | Effects |
| [wah‑wah] | Speaker sounds like wah-wah effect | Effects |
| [echo] | Speaker sounds like echo effect | Effects |
| [reverb] | Speaker sounds like reverb effect | Effects |
| [delay] | Speaker sounds like delay effect | Effects |
| [pitch shift down] | Speaker sounds like pitch shifted down | Effects |
| [pitch shift up] | Speaker sounds like pitch shifted up | Effects |
| [time stretch] | Speaker sounds like time stretched audio | Effects |
| [slow-mo] | Speaker sounds like slow motion effect | Effects |
| [fast-mo] | Speaker sounds like fast motion effect | Effects |
| [robotic stutter] | Speaker sounds like robotic stuttering effect | Effects |
| [syncopation] | Speaker sounds like syncopated rhythm effect | Effects |
| [vibrato] | Speaker sounds like vibrato effect | Effects |
| [tremolo] | Speaker sounds like tremolo effect | Effects |
| [filter sweep] | Speaker sounds like filter sweep effect | Effects |
| [low pass filter] | Speaker sounds like low pass filtered | Effects |
| [high pass filter] | Speaker sounds like high pass filtered | Effects |
| [bandpass] | Speaker sounds like bandpass filtered | Effects |
| [band reject] | Speaker sounds like band reject filtered | Effects |
| [granular] | Speaker sounds like granular synthesis effect | Effects |
| [noise gate] | Speaker sounds like noise gated | Effects |
| [compressor snap] | Speaker sounds like compressed with snap | Effects |
| [expander] | Speaker sounds like expanded audio | Effects |
| [flanging] | Speaker sounds like flanging effect | Effects |
| [phasing] | Speaker sounds like phasing effect | Effects |
| [chorus] | Speaker sounds like chorus effect | Effects |
| [tremolo effect] | Speaker sounds like tremolo audio effect | Effects |
| [ring modulation] | Speaker sounds like ring modulation effect | Effects |
| [auto‑tune] | Speaker sounds like auto-tuned | Effects |
| [harmonizer] | Speaker sounds like harmonizer effect | Effects |
| [robotic echo] | Speaker sounds like robotic echo effect | Effects |
| [metallic sheen] | Speaker sounds like metallic audio effect | Effects |
| [telephone filter] | Speaker sounds like telephone filtered | Effects |
| [megaphone] | Speaker sounds like megaphone effect | Effects |
| [speaking through mask] | Speaker sounds like speaking through mask | Effects |
| [Radio Broadcast] | Speaker sounds like radio broadcast effect | Effects |
| [alarm modulation] | Speaker sounds like alarm modulation effect | Effects |
| [radio static] | Speaker sounds like radio static effect | Effects |
| [vinyl crackle] | Speaker sounds like vinyl record crackle | Effects |
| [audiobook chassis] | Speaker sounds like audiobook processing | Effects |
| [hard‑clip] | Speaker sounds like hard clipped audio | Effects |
| [soft‑clip] | Speaker sounds like soft clipped audio | Effects |
| [digital clip] | Speaker sounds like digital clipping | Effects |
| [bitrate drop] | Speaker sounds like reduced bitrate | Effects |
| [sample‑rate reduction] | Speaker sounds like reduced sample rate | Effects |
| [robotic sequence] | Speaker sounds like robotic sequence effect | Effects |
| [cybernetic glitch] | Speaker sounds like cybernetic glitch effect | Effects |
| [data‑corrupt] | Speaker sounds like corrupted data | Effects |
| [waveform bend] | Speaker sounds like bent waveform | Effects |
| [sine wave tone] | Speaker sounds like sine wave tone | Effects |
| [square wave tone] | Speaker sounds like square wave tone | Effects |
| [sawtooth tone] | Speaker sounds like sawtooth wave tone | Effects |
| [white noise sweep] | Speaker sounds like white noise sweep | Effects |
| [pink noise] | Speaker sounds like pink noise effect | Effects |
| [brown noise] | Speaker sounds like brown noise effect | Effects |
| [detuned] | Speaker sounds detuned | Effects |
| [lo‑fi] | Speaker sounds lo-fi processed | Effects |
| [hi‑fi] | Speaker sounds hi-fi processed | Effects |
| [vintage mic] | Speaker sounds like vintage microphone | Effects |
| [tube warmth] | Speaker sounds like tube amplifier warmth | Effects |
| [solid state mic] | Speaker sounds like solid state microphone | Effects |
| [dynamic mic proximity] | Speaker sounds like close dynamic microphone | Effects |
| [condenser mic room] | Speaker sounds like condenser microphone in room | Effects |
| [studio room tone] | Speaker sounds like studio room tone | Effects |
| [live stage echo] | Speaker sounds like live stage echo | Effects |
| [concert hall reverb] | Speaker sounds like concert hall reverb | Effects |
| [church hall reverb] | Speaker sounds like church hall reverb | Effects |
| [submarine filter] | Speaker sounds like underwater submarine filter | Effects |
| [underwater murmur] | Speaker sounds like underwater murmur | Effects |
| [telephone ring] | Speaker sounds like telephone ring effect | Effects |
| [fax beep] | Speaker sounds like fax machine beep | Effects |
| [dial‑up tone] | Speaker sounds like dial-up modem tone | Effects |
| [modem handshake] | Speaker sounds like modem handshake | Effects |
| [cassette wow] | Speaker sounds like cassette tape wow effect | Effects |
| [walkman hiss] | Speaker sounds like walkman tape hiss | Effects |
| [8‑bit chiptune] | Speaker sounds like 8-bit chiptune | Effects |
| [gameboy voice] | Speaker sounds like Game Boy audio | Effects |
| [arcade beep] | Speaker sounds like arcade machine beep | Effects |
| [retro synth] | Speaker sounds like retro synthesizer | Effects |
| [dense pad] | Speaker sounds like dense synthesizer pad | Effects |
| [looper delay] | Speaker sounds like looper delay effect | Effects |
| [ping‑pong delay] | Speaker sounds like ping-pong delay | Effects |
| [reverse reverb] | Speaker sounds like reverse reverb effect | Effects |
| [ghost echo] | Speaker sounds like ghostly echo effect | Effects |
| [haunted reverb] | Speaker sounds like haunted reverb effect | Effects |
| [concert fade] | Speaker sounds like concert fade effect | Effects |
| [whoosh filter] | Speaker sounds like whoosh filter effect | Effects |
| [jazz tape] | Speaker sounds like jazz tape effect | Effects |
| [spread chorus] | Speaker sounds like spread chorus effect | Effects |
| [bass boost] | Speaker sounds like bass boosted | Effects |
| [treble cut] | Speaker sounds like treble cut | Effects |
| [mid scoop] | Speaker sounds like mid-range scooped | Effects |
| [stereo widen] | Speaker sounds like stereo widened | Effects |
| [mono fold] | Speaker sounds like mono folded | Effects |
| [sidechain pump] | Speaker sounds like sidechain pumping | Effects |
| [ducking] | Speaker sounds like ducking effect | Effects |
| [side‑tone] | Speaker sounds like side-tone effect | Effects |
| [talkback mic] | Speaker sounds like talkback microphone | Effects |
| [isolated mic] | Speaker sounds like isolated microphone | Effects |
| [ambi mic] | Speaker sounds like ambient microphone | Effects |
| [close mic] | Speaker sounds like close microphone | Effects |
| [room mic] | Speaker sounds like room microphone | Effects |
| [playback sped‑up] | Speaker sounds like sped-up playback | Effects |
| [playback slowed‑down] | Speaker sounds like slowed-down playback | Effects |
| [stabilize tone] | Speaker sounds like tone stabilized | Effects |
| [digital shimmer] | Speaker sounds like digital shimmer effect | Effects |
| [backmasking] | Speaker sounds like backmasked audio | Effects |
| [reverse playback] | Speaker sounds like reverse playback | Effects |
| [tape stop] | Speaker sounds like tape stop effect | Effects |
| [LED buzz] | Speaker sounds like LED buzzing | Effects |
| [machine whir] | Speaker sounds like machine whirring | Effects |
| [gear shift] | Speaker sounds like gear shifting | Effects |
| [servo buzz] | Speaker sounds like servo motor buzzing | Effects |
| [microphone feedback] | Speaker sounds like microphone feedback | Effects |
| [PA system echo] | Speaker sounds like PA system echo | Effects |
| [live mic pop] | Speaker sounds like live microphone pop | Effects |
| [strong british accent] | Speaker speaks with a strong British Accent. | Accents |
| [strong american accent] | Speaker speaks with a strong American Accent. | Accents |
| [strong australian accent] | Speaker speaks with a strong Australian Accent. | Accents |
| [strong canadian accent] | Speaker speaks with a strong Canadian Accent. | Accents |
| [strong irish accent] | Speaker speaks with a strong Irish Accent. | Accents |
| [strong scottish accent] | Speaker speaks with a strong Scottish Accent. | Accents |
| [strong french accent] | Speaker speaks with a strong French Accent. | Accents |
| [strong german accent] | Speaker speaks with a strong German Accent. | Accents |
| [strong italian accent] | Speaker speaks with a strong Italian Accent. | Accents |
| [strong spanish accent] | Speaker speaks with a strong Spanish Accent. | Accents |
| [strong mexican accent] | Speaker speaks with a strong Mexican Accent. | Accents |
| [strong brazilian accent] | Speaker speaks with a strong Brazilian Accent. | Accents |
| [strong indian accent] | Speaker speaks with a strong Indian Accent. | Accents |
| [strong south african accent] | Speaker speaks with a strong South African Accent. | Accents |
| [strong russian accent] | Speaker speaks with a strong Russian Accent. | Accents |
| [strong chinese accent] | Speaker speaks with a strong Chinese Accent. | Accents |
| [strong japanese accent] | Speaker speaks with a strong Japanese Accent. | Accents |
| [strong korean accent] | Speaker speaks with a strong Korean Accent. | Accents |
| [strong dutch accent] | Speaker speaks with a strong Dutch Accent. | Accents |
| [strong swedish accent] | Speaker speaks with a strong Swedish Accent. | Accents |
| [strong norwegian accent] | Speaker speaks with a strong Norwegian Accent. | Accents |
| [strong danish accent] | Speaker speaks with a strong Danish Accent. | Accents |
| [strong finnish accent] | Speaker speaks with a strong Finnish Accent. | Accents |
| [strong polish accent] | Speaker speaks with a strong Polish Accent. | Accents |
| [strong ukrainian accent] | Speaker speaks with a strong Ukrainian Accent. | Accents |
| [strong turkish accent] | Speaker speaks with a strong Turkish Accent. | Accents |
| [strong arabic accent] | Speaker speaks with a strong Arabic Accent. | Accents |
| [strong portuguese accent] | Speaker speaks with a strong Portuguese Accent. | Accents |
| [strong caribbean accent] | Speaker speaks with a strong Caribbean Accent. | Accents |
| [strong jamaican accent] | Speaker speaks with a strong Jamaican Accent. | Accents |
| [strong new zealand accent] | Speaker speaks with a strong New Zealand Accent. | Accents |
| [strong south us accent] | Speaker speaks with a strong South US Accent. | Accents |
| [strong texas accent] | Speaker speaks with a strong Texas Accent. | Accents |
| [strong southern us accent] | Speaker speaks with a strong Southern US Accent. | Accents |
| [strong midwestern accent] | Speaker speaks with a strong Midwestern Accent. | Accents |
| [strong eastern us accent] | Speaker speaks with a strong Eastern US Accent. | Accents |
| [strong californian accent] | Speaker speaks with a strong Californian Accent. | Accents |
| [strong southeastern us accent] | Speaker speaks with a strong Southeastern US Accent. | Accents |
| [strong western us accent] | Speaker speaks with a strong Western US Accent. | Accents |
| [strong latin american accent] | Speaker speaks with a strong Latin American Accent. | Accents |
| [strong argentinian accent] | Speaker speaks with a strong Argentinian Accent. | Accents |
| [strong chilean accent] | Speaker speaks with a strong Chilean Accent. | Accents |
| [strong colombian accent] | Speaker speaks with a strong Colombian Accent. | Accents |
| [strong peruvian accent] | Speaker speaks with a strong Peruvian Accent. | Accents |
| [strong venezuelan accent] | Speaker speaks with a strong Venezuelan Accent. | Accents |
| [strong egyptian accent] | Speaker speaks with a strong Egyptian Accent. | Accents |
| [strong moroccan accent] | Speaker speaks with a strong Moroccan Accent. | Accents |
| [strong tunisian accent] | Speaker speaks with a strong Tunisian Accent. | Accents |
| [strong gulf arabic accent] | Speaker speaks with a strong Gulf Arabic Accent. | Accents |
| [strong afghan accent] | Speaker speaks with a strong Afghan Accent. | Accents |
| [strong pakistani accent] | Speaker speaks with a strong Pakistani Accent. | Accents |
| [strong bangladeshi accent] | Speaker speaks with a strong Bangladeshi Accent. | Accents |
| [strong sri lankan accent] | Speaker speaks with a strong Sri Lankan Accent. | Accents |
| [strong indonesian accent] | Speaker speaks with a strong Indonesian Accent. | Accents |
| [strong malaysian accent] | Speaker speaks with a strong Malaysian Accent. | Accents |
| [strong filipino accent] | Speaker speaks with a strong Filipino Accent. | Accents |
| [strong vietnamese accent] | Speaker speaks with a strong Vietnamese Accent. | Accents |
| [strong thai accent] | Speaker speaks with a strong Thai Accent. | Accents |
| [strong cambodian accent] | Speaker speaks with a strong Cambodian Accent. | Accents |
| [strong lao accent] | Speaker speaks with a strong Lao Accent. | Accents |
| [strong mongolian accent] | Speaker speaks with a strong Mongolian Accent. | Accents |
| [strong nepalese accent] | Speaker speaks with a strong Nepalese Accent. | Accents |
| [strong bengali accent] | Speaker speaks with a strong Bengali Accent. | Accents |
| [strong punjabi accent] | Speaker speaks with a strong Punjabi Accent. | Accents |
| [strong gujarati accent] | Speaker speaks with a strong Gujarati Accent. | Accents |
| [strong tamil accent] | Speaker speaks with a strong Tamil Accent. | Accents |
| [strong telugu accent] | Speaker speaks with a strong Telugu Accent. | Accents |
| [strong marathi accent] | Speaker speaks with a strong Marathi Accent. | Accents |
| [strong urdu accent] | Speaker speaks with a strong Urdu Accent. | Accents |
| [strong persian accent] | Speaker speaks with a strong Persian Accent. | Accents |
| [strong hebrew accent] | Speaker speaks with a strong Hebrew Accent. | Accents |
| [strong swahili accent] | Speaker speaks with a strong Swahili Accent. | Accents |
| [strong zulu accent] | Speaker speaks with a strong Zulu Accent. | Accents |
| [strong xhosa accent] | Speaker speaks with a strong Xhosa Accent. | Accents |
| [strong yoruba accent] | Speaker speaks with a strong Yoruba Accent. | Accents |
| [strong igbo accent] | Speaker speaks with a strong Igbo Accent. | Accents |
| [strong somali accent] | Speaker speaks with a strong Somali Accent. | Accents |
| [strong armenian accent] | Speaker speaks with a strong Armenian Accent. | Accents |
| [strong georgian accent] | Speaker speaks with a strong Georgian Accent. | Accents |
| [strong kazakh accent] | Speaker speaks with a strong Kazakh Accent. | Accents |
| [strong greek accent] | Speaker speaks with a strong Greek Accent. | Accents |
| [strong romanian accent] | Speaker speaks with a strong Romanian Accent. | Accents |
| [strong hungarian accent] | Speaker speaks with a strong Hungarian Accent. | Accents |
| [strong czech accent] | Speaker speaks with a strong Czech Accent. | Accents |
| [strong slovak accent] | Speaker speaks with a strong Slovak Accent. | Accents |
| [strong croatian accent] | Speaker speaks with a strong Croatian Accent. | Accents |
| [strong serbian accent] | Speaker speaks with a strong Serbian Accent. | Accents |
| [strong bosnian accent] | Speaker speaks with a strong Bosnian Accent. | Accents |
| [strong bulgarian accent] | Speaker speaks with a strong Bulgarian Accent. | Accents |
| [strong estonian accent] | Speaker speaks with a strong Estonian Accent. | Accents |
| [strong latvian accent] | Speaker speaks with a strong Latvian Accent. | Accents |
| [strong lithuanian accent] | Speaker speaks with a strong Lithuanian Accent. | Accents |
| [strong malta accent] | Speaker speaks with a strong Maltese Accent. | Accents |
| [strong icelandic accent] | Speaker speaks with a strong Icelandic Accent. | Accents |
| [strong welsh accent] | Speaker speaks with a strong Welsh Accent. | Accents |
| [strong catalan accent] | Speaker speaks with a strong Catalan Accent. | Accents |
| [strong basque accent] | Speaker speaks with a strong Basque Accent. | Accents |
| [strong galician accent] | Speaker speaks with a strong Galician Accent. | Accents |
| [strong yiddish accent] | Speaker speaks with a strong Yiddish Accent. | Accents |
| [strong esperanto accent] | Speaker speaks with a strong Esperanto Accent. | Accents |
| [strong fictional alien accent] | Speaker speaks with a strong Fictional Alien Accent. | Accents |
| [strong pirate accent] | Speaker speaks with a strong Pirate Accent. | Accents |
| [strong robot accent] | Speaker speaks with a strong Robot Accent. | Accents |
| [deadpan delivery] | Speaker delivers humor with a flat, emotionless tone | Humor |
| [self-deprecating chuckle] | Speaker chuckles while making fun of themselves | Humor |
| [sarcastic remark] | Speaker makes a sarcastic humorous comment | Humor |
| [wry grin] | Speaker sounds like they have a wry, knowing smile | Humor |
| [playful banter] | Speaker engages in light, playful humorous exchange | Humor |
| [Environment irony] | Speaker uses ironic humor based on the situation | Humor |
| [hyperbole] | Speaker uses exaggerated humor for comedic effect | Humor |
| [understatement] | Speaker uses understated humor for comedic effect | Humor |
| [pun delivery] | Speaker delivers a pun with comedic timing | Humor |
| [dad joke tone] | Speaker uses the classic dad joke delivery style | Humor |
| [groan joke] | Speaker tells a joke that makes people groan | Humor |
| [laugh track] | Speaker sounds like canned television laughter | Humor |
| [canned laughter] | Speaker sounds like artificial recorded laughter | Humor |
| [awkward laugh] | Speaker laughs awkwardly in an uncomfortable way | Humor |
| [nervous chuckle] | Speaker chuckles nervously | Humor |
| [giggle fit] | Speaker breaks into uncontrolled giggling | Humor |
| [snarky comment] | Speaker makes a snarky, witty remark | Humor |
| [witty aside] | Speaker makes a clever witty comment | Humor |
| [dry humor] | Speaker uses dry, understated humor | Humor |
| [absurd punchline] | Speaker delivers an absurd comedic punchline | Humor |
| [whimsical humor] | Speaker uses playful, whimsical comedy | Humor |
| [slapstick sound] | Speaker sounds like physical slapstick comedy | Humor |
| [mime gag] | Speaker sounds like performing mime comedy | Humor |
| [comic timing] | Speaker uses perfect comedic timing | Humor |
| [improvised joke] | Speaker makes up humor on the spot | Humor |
| [callback joke] | Speaker references an earlier joke | Humor |
| [running gag] | Speaker continues a recurring comedic element | Humor |
| [ironic gasp] | Speaker gasps ironically for comedic effect | Humor |
| [sardonic sigh] | Speaker sighs with sardonic humor | Humor |
| [mock seriousness] | Speaker pretends to be serious for humor | Humor |
| [joke setup] | Speaker sets up a joke with proper buildup | Humor |
| [comedic pause] | Speaker pauses for comedic effect | Humor |
| [physical comedy] | Speaker sounds like performing physical comedy | Humor |
| [fart joke] | Speaker makes crude bodily function humor | Humor |
| [toot sound] | Speaker makes silly tooting sounds | Humor |
| [burp laughter] | Speaker laughs while burping | Humor |
| [pratfall sound] | Speaker sounds like falling comedically | Humor |
| [boing sound] | Speaker makes cartoon boing sound effects | Humor |
| [whoopee cushion] | Speaker sounds like a whoopee cushion | Humor |
| [pie-in-face] | Speaker sounds like getting hit with a pie | Humor |
| [spoof trailer] | Speaker sounds like a parody movie trailer | Humor |
| [parody intro] | Speaker sounds like a parody introduction | Humor |
| [knock-knock joke] | Speaker tells a knock-knock joke | Humor |
| [misheard pun] | Speaker makes a pun based on mishearing | Humor |
| [punny pun] | Speaker makes an especially punny joke | Humor |
| [meta joke] | Speaker makes a joke about jokes themselves | Humor |
| [fourth-wall break] | Speaker breaks character for comedic effect | Humor |
| [character trope] | Speaker plays up comedic character stereotypes | Humor |
| [cliché delivery] | Speaker deliberately uses clichéd humor | Humor |
| [comic relief] | Speaker provides comedic relief in tense moments | Humor |
| [satire bite] | Speaker uses biting satirical humor | Humor |
| [mock horror] | Speaker pretends to be horrified for comedy | Humor |
| [over-the-top villain laugh] | Speaker does an exaggerated evil laugh | Humor |
| [campy tone] | Speaker uses deliberately campy humor | Humor |
| [campy gasp] | Speaker gasps in an over-the-top campy way | Humor |
| [exaggerated gasp] | Speaker gasps dramatically for comedic effect | Humor |
| [overdramatic gasp] | Speaker gasps with extreme drama | Humor |
| [silly whisper] | Speaker whispers in a silly comedic way | Humor |
| [silly shout] | Speaker shouts in a silly comedic way | Humor |
| [cartoon voice] | Speaker uses an exaggerated cartoon voice | Humor |
| [chipmunk voice] | Speaker uses a high-pitched chipmunk voice | Humor |
| [deep comedic voice] | Speaker uses an exaggerated deep voice | Humor |
| [accented pun] | Speaker makes puns using accents | Humor |
| [weekday humor] | Speaker makes jokes about weekdays | Humor |
| [dad vibe] | Speaker has a stereotypical dad humor energy | Humor |
| [mom voice] | Speaker uses stereotypical mom humor voice | Humor |
| [one-liner] | Speaker delivers a quick one-line joke | Humor |
| [fun fact aside] | Speaker shares amusing trivia | Humor |
| [irreverent aside] | Speaker makes irreverent humorous comments | Humor |
| [teasing tone] | Speaker uses a playful teasing tone | Humor |
| [playful insult] | Speaker makes playful insulting humor | Humor |
| [compliment sandwich] | Speaker uses backhanded compliment humor | Humor |
| [tongue-in-cheek] | Speaker uses tongue-in-cheek humor | Humor |
| [wink sound] | Speaker sounds like winking for comedic effect | Humor |
| [snort laugh] | Speaker snorts while laughing | Humor |
| [belch sound] | Speaker makes belching sounds for humor | Humor |
| [mock applause] | Speaker gives fake applause for comedic effect | Humor |
| [cheesy joke] | Speaker tells deliberately cheesy jokes | Humor |
| [corny pun] | Speaker makes corny puns | Humor |
| [blue joke] | Speaker tells slightly risqué humor | Humor |
| [dark joke] | Speaker uses dark comedy humor | Humor |
| [naughty wink] | Speaker sounds mischievously flirtatious | Humor |
| [flirty joke] | Speaker makes flirtatious humor | Humor |
| [sexy gasp] | Speaker gasps in a playfully sexy way | Humor |
| [romantic joke] | Speaker makes romantic comedy humor | Humor |
| [dry sarcasm] | Speaker uses very dry sarcastic humor | Humor |
| [friendly tease] | Speaker teases in a friendly way | Humor |
| [competitive banter] | Speaker engages in competitive humorous banter | Humor |
| [team huddle joke] | Speaker makes team-spirited humor | Humor |
| [office humor] | Speaker makes workplace-related humor | Humor |
| [geek joke] | Speaker makes geeky humor references | Humor |
| [nerd reference] | Speaker makes nerdy humor references | Humor |
| [inside joke] | Speaker makes humor only certain people understand | Humor |
| [pop culture nod] | Speaker references popular culture humorously | Humor |
| [spoiler joke] | Speaker makes humor about spoilers | Humor |
| [spoof news] | Speaker sounds like parody news reporting | Humor |
| [mock announcement] | Speaker makes fake announcements for humor | Humor |
| [false disclaimer] | Speaker gives fake disclaimers for comedy | Humor |
| [silly disclaimer] | Speaker gives silly disclaimers | Humor |
| [tongue twist] | Speaker plays with tongue twisters humorously | Humor |
| [rap joke] | Speaker makes rap-style humor | Humor |
| [beatbox joke] | Speaker makes beatboxing humor | Humor |
| [comedy beat] | Speaker uses musical comedy timing | Humor |
| [punchline drum beat] | Speaker times punchlines with drum beats | Humor |
| [rimshot] | Speaker uses classic rimshot comedy timing | Humor |
| [rimshot flourish] | Speaker adds flourish to rimshot comedy | Humor |
| [cartoon sound effect] | Speaker makes cartoon-style sound effects | Humor |
| [prank call tone] | Speaker sounds like making prank calls | Humor |
| [mock serious tone] | Speaker pretends to be serious for humor | Humor |
| [lawyer joke] | Speaker makes lawyer-related humor | Humor |
| [doctor joke] | Speaker makes medical humor | Humor |
| [tech geek joke] | Speaker makes technology-related humor | Humor |
| [programmer pun] | Speaker makes programming-related puns | Humor |
| [movie reference] | Speaker references movies humorously | Humor |
| [TV show reference] | Speaker references TV shows humorously | Humor |
| [meme reference] | Speaker references internet memes humorously | Humor |
| [self-reflective] | Speaker conveys self-reflection and thoughtful introspection | Introspective |
| [self-doubt] | Speaker conveys self-doubt and uncertainty | Introspective |
| [self-critical] | Speaker conveys self-criticism and inner judgment | Introspective |
| [self-aware] | Speaker conveys heightened self-awareness | Introspective |
| [quiet reflection] | Speaker conveys quiet, inward reflection | Introspective |
| [inner calm] | Speaker conveys inner calm and serenity | Introspective |
| [inner turmoil] | Speaker conveys inner turmoil and conflict | Introspective |
| [soul-searching] | Speaker conveys deep soul-searching | Introspective |
| [nihilistic thought] | Speaker conveys nihilistic thoughts and emptiness | Introspective |
| [existential dread] | Speaker conveys existential dread and anxiety | Introspective |
| [existential wonder] | Speaker conveys existential wonder and curiosity | Introspective |
| [existential calm] | Speaker conveys existential calm and acceptance | Introspective |
| [philosophical musing] | Speaker conveys philosophical musings | Introspective |
| [philosophical doubt] | Speaker conveys philosophical doubt and questioning | Introspective |
| [philosophical insight] | Speaker conveys philosophical insight and clarity | Introspective |
| [inner peace] | Speaker conveys inner peace and harmony | Introspective |
| [inner conflict] | Speaker conveys inner conflict and struggle | Introspective |
| [mental fatigue] | Speaker conveys mental fatigue and weariness | Introspective |
| [mental clarity] | Speaker conveys mental clarity and focus | Introspective |
| [mental block] | Speaker conveys a mental block and frustration | Introspective |
| [mental reset] | Speaker conveys need for a mental reset | Introspective |
| [mental chatter] | Speaker conveys restless mental chatter | Introspective |
| [spiritual questioning] | Speaker conveys spiritual questioning | Introspective |
| [spiritual awakening] | Speaker conveys a spiritual awakening | Introspective |
| [spiritual doubt] | Speaker conveys spiritual doubt and hesitation | Introspective |
| [spiritual longing] | Speaker conveys spiritual longing | Introspective |
| [soulful sigh] | Speaker lets out a soulful sigh | Introspective |
| [soulful pause] | Speaker pauses with a soulful tone | Introspective |
| [soulful tone] | Speaker speaks with a soulful tone | Introspective |
| [heartfelt reflection] | Speaker conveys heartfelt reflection | Introspective |
| [heartfelt pause] | Speaker pauses with heartfelt emotion | Introspective |
| [heartfelt realization] | Speaker conveys a heartfelt realization | Introspective |
| [quiet confession] | Speaker makes a quiet confession | Introspective |
| [soft confession] | Speaker makes a soft confession | Introspective |
| [hidden regret] | Speaker reveals hidden regret | Introspective |
| [hidden shame] | Speaker reveals hidden shame | Introspective |
| [growing acceptance] | Speaker conveys growing acceptance | Introspective |
| [reluctant acceptance] | Speaker conveys reluctant acceptance | Introspective |
| [emotional numbness] | Speaker conveys emotional numbness | Introspective |
| [emotional overload] | Speaker conveys emotional overload | Introspective |
| [emotional breakthrough] | Speaker conveys an emotional breakthrough | Introspective |
| [emotional release] | Speaker conveys emotional release | Introspective |
| [emotional block] | Speaker conveys emotional block | Introspective |
| [emotional honesty] | Speaker conveys emotional honesty | Introspective |
| [emotional veil] | Speaker conveys an emotional veil | Introspective |
| [nostalgic reflection] | Speaker conveys nostalgic reflection | Introspective |
| [nostalgic longing] | Speaker conveys nostalgic longing | Introspective |
| [nostalgic ache] | Speaker conveys a nostalgic ache | Introspective |
| [melancholic reflection] | Speaker conveys melancholic reflection | Introspective |
| [melancholic sigh] | Speaker releases a melancholic sigh | Introspective |
| [melancholic tone] | Speaker speaks with a melancholic tone | Introspective |
| [wistful reflection] | Speaker conveys wistful reflection | Introspective |
| [wistful longing] | Speaker conveys wistful longing | Introspective |
| [wistful sigh] | Speaker releases a wistful sigh | Introspective |
| [restless thinking] | Speaker conveys restless thinking | Introspective |
| [restless pause] | Speaker pauses restlessly | Introspective |
| [restless tone] | Speaker speaks with a restless tone | Introspective |
| [anxious reflection] | Speaker conveys anxious reflection | Introspective |
| [anxious pause] | Speaker pauses anxiously | Introspective |
| [anxious tone] | Speaker speaks with an anxious tone | Introspective |
| [hopeful reflection] | Speaker conveys hopeful reflection | Introspective |
| [hopeful sigh] | Speaker releases a hopeful sigh | Introspective |
| [hopeful tone] | Speaker speaks with a hopeful tone | Introspective |
| [resigned reflection] | Speaker conveys resigned reflection | Introspective |
| [resigned sigh] | Speaker releases a resigned sigh | Introspective |
| [resigned tone] | Speaker speaks with a resigned tone | Introspective |
| [regretful reflection] | Speaker conveys regretful reflection | Introspective |
| [regretful sigh] | Speaker releases a regretful sigh | Introspective |
| [regretful tone] | Speaker speaks with a regretful tone | Introspective |
| [defensive reflection] | Speaker conveys defensive reflection | Introspective |
| [defensive tone] | Speaker speaks with a defensive tone | Introspective |
| [guarded reflection] | Speaker conveys guarded reflection | Introspective |
| [guarded tone] | Speaker speaks with a guarded tone | Introspective |
| [vulnerable whisper] | Speaker whispers vulnerably | Introspective |
| [vulnerable tone] | Speaker speaks with a vulnerable tone | Introspective |
| [shameful whisper] | Speaker whispers with shame | Introspective |
| [ashamed tone] | Speaker speaks with an ashamed tone | Introspective |
| [lonely reflection] | Speaker conveys lonely reflection | Introspective |
| [lonely sigh] | Speaker releases a lonely sigh | Introspective |
| [lonely tone] | Speaker speaks with a lonely tone | Introspective |
| [isolated whisper] | Speaker whispers in isolation | Introspective |
| [isolated tone] | Speaker speaks with an isolated tone | Introspective |
| [detached reflection] | Speaker conveys detached reflection | Introspective |
| [detached tone] | Speaker speaks with a detached tone | Introspective |
| [contemplative silence] | Speaker sits in contemplative silence | Introspective |
| [contemplative sigh] | Speaker releases a contemplative sigh | Introspective |
| [contemplative tone] | Speaker speaks with a contemplative tone | Introspective |
| [meditative silence] | Speaker rests in meditative silence | Introspective |
| [meditative sigh] | Speaker releases a meditative sigh | Introspective |
| [meditative tone] | Speaker speaks with a meditative tone | Introspective |
| [introspective silence] | Speaker rests in introspective silence | Introspective |
| [introspective sigh] | Speaker releases an introspective sigh | Introspective |
| [introspective hum] | Speaker hums introspectively | Introspective |
| [introspective tone] | Speaker speaks with an introspective tone | Introspective |
| [inner dialogue] | Speaker engages in inner dialogue | Introspective |
| [inner monologue tone] | Speaker speaks in an inner monologue tone | Introspective |
| [inner question] | Speaker poses an inner question | Introspective |
| [inner answer] | Speaker offers an inner answer | Introspective |
| [inner doubt] | Speaker expresses inner doubt | Introspective |
| [inner conflict] | Speaker expresses inner conflict | Introspective |
| [inner pain] | Speaker expresses inner pain | Introspective |
| [inner resolve] | Speaker expresses inner resolve | Introspective |
| [inner strength] | Speaker expresses inner strength | Introspective |
| [inner weakness] | Speaker expresses inner weakness | Introspective |
| [mental rewind] | Speaker mentally rewinds events | Introspective |
| [mental fast-forward] | Speaker mentally fast-forwards events | Introspective |
| [mental pause] | Speaker takes a mental pause | Introspective |
| [mental echo] | Speaker experiences a mental echo | Introspective |
| [memory echo] | Speaker experiences a memory echo | Introspective |
| [memory flash] | Speaker experiences a memory flash | Introspective |
| [memory pause] | Speaker pauses on a memory | Introspective |
| [memory ache] | Speaker conveys a memory ache | Introspective |
| [memory warmth] | Speaker conveys memory warmth | Introspective |
| [memory chill] | Speaker conveys memory chill | Introspective |
| [flashback whisper] | Speaker whispers a flashback | Introspective |
| [flashback tone] | Speaker speaks in a flashback tone | Introspective |
| [flashback sigh] | Speaker releases a flashback sigh | Introspective |
| [past reflection] | Speaker reflects on the past | Introspective |
| [past regret] | Speaker conveys past regret | Introspective |
| [future fear] | Speaker conveys fear of the future | Introspective |
| [future hope] | Speaker conveys hope for the future | Introspective |
| [future reflection] | Speaker reflects on the future | Introspective |
| [future uncertainty] | Speaker conveys future uncertainty | Introspective |
| [present moment] | Speaker focuses on the present moment | Introspective |
| [present awareness] | Speaker conveys present awareness | Introspective |
| [present calm] | Speaker conveys present calm | Introspective |
| [present unrest] | Speaker conveys present unrest | Introspective |
| [meaning search] | Speaker searches for meaning | Introspective |
| [meaning found] | Speaker conveys meaning found | Introspective |
| [meaning lost] | Speaker conveys meaning lost | Introspective |
| [truth-seeking] | Speaker seeks the truth | Introspective |
| [truth found] | Speaker conveys truth found | Introspective |
| [truth hidden] | Speaker conveys truth hidden | Introspective |
| [truth whispered] | Speaker whispers a hidden truth | Introspective |
| [gunshot] | Sound of gunshot firing | Sound Effects |
| [explosion] | Sound of explosive blast | Sound Effects |
| [thunder] | Sound of thunder rumbling | Sound Effects |
| [lightning crack] | Sound of lightning striking | Sound Effects |
| [doorbell] | Sound of doorbell ringing | Sound Effects |
| [phone ringing] | Sound of telephone ringing | Sound Effects |
| [alarm clock] | Sound of alarm clock beeping | Sound Effects |
| [car engine] | Sound of car engine running | Sound Effects |
| [motorcycle roar] | Sound of motorcycle engine revving | Sound Effects |
| [helicopter] | Sound of helicopter blades rotating | Sound Effects |
| [airplane] | Sound of airplane flying overhead | Sound Effects |
| [train horn] | Sound of train horn blowing | Sound Effects |
| [siren] | Sound of emergency siren wailing | Sound Effects |
| [dog barking] | Sound of dog barking | Sound Effects |
| [cat meowing] | Sound of cat meowing | Sound Effects |
| [bird chirping] | Sound of birds chirping | Sound Effects |
| [rooster crow] | Sound of rooster crowing | Sound Effects |
| [cow mooing] | Sound of cow mooing | Sound Effects |
| [horse neighing] | Sound of horse neighing | Sound Effects |
| [lion roar] | Sound of lion roaring | Sound Effects |
| [wolf howl] | Sound of wolf howling | Sound Effects |
| [elephant trumpet] | Sound of elephant trumpeting | Sound Effects |
| [snake hiss] | Sound of snake hissing | Sound Effects |
| [bee buzzing] | Sound of bee buzzing | Sound Effects |
| [cricket chirp] | Sound of cricket chirping | Sound Effects |
| [footsteps] | Sound of footsteps walking | Sound Effects |
| [running steps] | Sound of running footsteps | Sound Effects |
| [heartbeat] | Sound of heartbeat pounding | Sound Effects |
| [clock ticking] | Sound of clock ticking | Sound Effects |
| [dripping water] | Sound of water dripping | Sound Effects |
| [flowing water] | Sound of water flowing | Sound Effects |
| [splash] | Sound of water splashing | Sound Effects |
| [bubble pop] | Sound of bubble popping | Sound Effects |
| [fire crackling] | Sound of fire crackling | Sound Effects |
| [wind howling] | Sound of wind howling | Sound Effects |
| [rain falling] | Sound of rain falling | Sound Effects |
| [glass breaking] | Sound of glass shattering | Sound Effects |
| [door creaking] | Sound of door creaking | Sound Effects |
| [door slamming] | Sound of door slamming shut | Sound Effects |
| [window opening] | Sound of window opening | Sound Effects |
| [zipper] | Sound of zipper opening or closing | Sound Effects |
| [paper ripping] | Sound of paper tearing | Sound Effects |
| [typing] | Sound of keyboard typing | Sound Effects |
| [mouse click] | Sound of computer mouse clicking | Sound Effects |
| [camera shutter] | Sound of camera taking photo | Sound Effects |
| [microwave beep] | Sound of microwave beeping | Sound Effects |
| [washing machine] | Sound of washing machine running | Sound Effects |
| [vacuum cleaner] | Sound of vacuum cleaner operating | Sound Effects |
| [hair dryer] | Sound of hair dryer running | Sound Effects |
| [electric drill] | Sound of electric drill operating | Sound Effects |
| [hammer hitting] | Sound of hammer hitting nail | Sound Effects |
| [saw cutting] | Sound of saw cutting wood | Sound Effects |
| [chainsaw] | Sound of chainsaw running | Sound Effects |
| [lawnmower] | Sound of lawnmower cutting grass | Sound Effects |
| [blender] | Sound of blender mixing | Sound Effects |
| [coffee grinder] | Sound of coffee beans grinding | Sound Effects |
| [toaster pop] | Sound of toaster popping up | Sound Effects |
| [kettle whistle] | Sound of kettle whistling | Sound Effects |
| [doorknob turn] | Sound of doorknob turning | Sound Effects |
| [key turning] | Sound of key turning in lock | Sound Effects |
| [coins dropping] | Sound of coins dropping | Sound Effects |
| [cash register] | Sound of cash register opening | Sound Effects |
| [pencil writing] | Sound of pencil writing on paper | Sound Effects |
| [marker squeaking] | Sound of marker on whiteboard | Sound Effects |
| [balloon pop] | Sound of balloon popping | Sound Effects |
| [cork pop] | Sound of cork popping from bottle | Sound Effects |
| [can opening] | Sound of can being opened | Sound Effects |
| [bottle opening] | Sound of bottle being opened | Sound Effects |
| [ice cubes] | Sound of ice cubes dropping in glass | Sound Effects |
| [soda fizz] | Sound of carbonated drink fizzing | Sound Effects |
| [whip crack] | Sound of whip cracking | Sound Effects |
| [sword clang] | Sound of metal sword clashing | Sound Effects |
| [arrow whoosh] | Sound of arrow flying through air | Sound Effects |
| [bow string] | Sound of bow string being released | Sound Effects |
| [shield clang] | Sound of shield being hit | Sound Effects |
| [armor clanking] | Sound of metal armor moving | Sound Effects |
| [horse galloping] | Sound of horse galloping | Sound Effects |
| [carriage wheels] | Sound of carriage wheels rolling | Sound Effects |
| [ship creaking] | Sound of wooden ship creaking | Sound Effects |
| [waves crashing] | Sound of ocean waves crashing | Sound Effects |
| [seagull cry] | Sound of seagull calling | Sound Effects |
| [whale song] | Sound of whale singing | Sound Effects |
| [dolphin click] | Sound of dolphin clicking | Sound Effects |
| [campfire] | Sound of campfire burning | Sound Effects |
| [logs falling] | Sound of logs falling | Sound Effects |
| [tent zipper] | Sound of tent zipper | Sound Effects |
| [hiking boots] | Sound of hiking boots on trail | Sound Effects |
| [river rapids] | Sound of river rapids flowing | Sound Effects |
| [owl hoot] | Sound of owl hooting | Sound Effects |
| [coyote howl] | Sound of coyote howling | Sound Effects |
| [frog ribbit] | Sound of frog croaking | Sound Effects |
| [cicada buzz] | Sound of cicada buzzing | Sound Effects |
| [mosquito buzz] | Sound of mosquito buzzing | Sound Effects |
| [fly buzzing] | Sound of fly buzzing | Sound Effects |
| [baby crying] | Sound of baby crying | Sound Effects |
| [child laughing] | Sound of child laughing | Sound Effects |
| [crowd cheering] | Sound of crowd cheering | Sound Effects |
| [crowd booing] | Sound of crowd booing | Sound Effects |
| [applause] | Sound of audience applauding | Sound Effects |
| [whistle blow] | Sound of whistle blowing | Sound Effects |
| [referee whistle] | Sound of sports referee whistle | Sound Effects |
| [ball bounce] | Sound of ball bouncing | Sound Effects |
| [basketball dribble] | Sound of basketball dribbling | Sound Effects |
| [tennis ball hit] | Sound of tennis ball being hit | Sound Effects |
| [golf club swing] | Sound of golf club swinging | Sound Effects |
| [bowling strike] | Sound of bowling ball hitting pins | Sound Effects |
| [dice roll] | Sound of dice rolling | Sound Effects |
| [cards shuffling] | Sound of playing cards shuffling | Sound Effects |
| [poker chips] | Sound of poker chips clinking | Sound Effects |
| [slot machine] | Sound of slot machine spinning | Sound Effects |
| [arcade game] | Sound of arcade game beeping | Sound Effects |
| [pinball] | Sound of pinball machine | Sound Effects |
| [carnival music] | Sound of carnival carousel music | Sound Effects |
| [ferris wheel] | Sound of ferris wheel turning | Sound Effects |
| [rollercoaster] | Sound of rollercoaster racing | Sound Effects |
| [fireworks] | Sound of fireworks exploding | Sound Effects |
| [party horn] | Sound of party horn blowing | Sound Effects |
| [balloon squeak] | Sound of balloon squeaking | Sound Effects |
| [confetti fall] | Sound of confetti falling | Sound Effects |
| [champagne cork] | Sound of champagne cork popping | Sound Effects |
| [church bell] | Sound of church bell ringing | Sound Effects |
| [school bell] | Sound of school bell ringing | Sound Effects |
| [grandfather clock] | Sound of grandfather clock chiming | Sound Effects |
| [cuckoo clock] | Sound of cuckoo clock | Sound Effects |
| [wind chimes] | Sound of wind chimes tinkling | Sound Effects |
| [music box] | Sound of music box playing | Sound Effects |
| [piano keys] | Sound of piano keys being pressed | Sound Effects |
| [guitar strum] | Sound of guitar being strummed | Sound Effects |
| [violin bow] | Sound of violin bow on strings | Sound Effects |
| [drum beat] | Sound of drum being beaten | Sound Effects |
| [cymbal crash] | Sound of cymbal crashing | Sound Effects |
| [trumpet blast] | Sound of trumpet playing | Sound Effects |
| [saxophone] | Sound of saxophone playing | Sound Effects |
| [harmonica] | Sound of harmonica playing | Sound Effects |
| [flute trill] | Sound of flute trilling | Sound Effects |
| [record player] | Sound of vinyl record playing | Sound Effects |
| [radio static] | Sound of radio static | Sound Effects |
| [TV static] | Sound of television static | Sound Effects |
| [remote click] | Sound of TV remote clicking | Sound Effects |
| [printer] | Sound of printer printing | Sound Effects |
| [fax machine] | Sound of fax machine operating | Sound Effects |
| [photocopier] | Sound of photocopier running | Sound Effects |
| [shredder] | Sound of paper shredder | Sound Effects |
| [stapler] | Sound of stapler stapling | Sound Effects |
| [hole punch] | Sound of hole punch punching | Sound Effects |
| [scissors cutting] | Sound of scissors cutting | Sound Effects |
| [velcro rip] | Sound of velcro being separated | Sound Effects |
| [bubble wrap] | Sound of bubble wrap popping | Sound Effects |
| [tape dispenser] | Sound of tape being pulled | Sound Effects |
| [rubber stamp] | Sound of rubber stamp stamping | Sound Effects |
| [page flip] | Sound of book page turning | Sound Effects |
| [book close] | Sound of book closing | Sound Effects |
| [newspaper rustle] | Sound of newspaper rustling | Sound Effects |
| [magazine flip] | Sound of magazine pages flipping | Sound Effects |
| [pen click] | Sound of pen clicking | Sound Effects |
| [chalk squeak] | Sound of chalk on blackboard | Sound Effects |
| [whisper] | Speaker speaks in a soft whisper | Styles |
| [shout] | Speaker speaks loudly and forcefully | Styles |
| [mumble] | Speaker speaks unclearly and quietly | Styles |
| [articulate] | Speaker speaks clearly and precisely | Styles |
| [fast speaking] | Speaker talks rapidly | Styles |
| [slow speaking] | Speaker talks slowly and deliberately | Styles |
| [rushed] | Speaker speaks hurriedly | Styles |
| [deliberate] | Speaker speaks with careful intention | Styles |
| [conversational] | Speaker uses casual conversation style | Styles |
| [formal] | Speaker uses formal speaking style | Styles |
| [casual] | Speaker uses relaxed informal style | Styles |
| [theatrical] | Speaker uses dramatic performance style | Styles |
| [energetic] | Speaker speaks with high energy | Styles |
| [monotone] | Speaker speaks in flat unchanging tone | Styles |
| [rhythmic] | Speaker speaks with musical rhythm | Styles |
| [staccato] | Speaker speaks in short choppy bursts | Styles |
| [breathy] | Speaker speaks with breathy vocal quality | Styles |
| [crisp] | Speaker speaks with sharp clear diction | Styles |
| [smooth] | Speaker speaks with flowing smooth delivery | Styles |
| [choppy] | Speaker speaks in disconnected segments | Styles |
| [measured] | Speaker speaks with careful pacing | Styles |
| [clipped] | Speaker speaks with abrupt short phrases | Styles |
| [drawling] | Speaker speaks with extended vowel sounds | Styles |
| [rapid-fire] | Speaker speaks extremely quickly | Styles |
| [languid] | Speaker speaks slowly and lazily | Styles |
| [animated] | Speaker speaks with lively expression | Styles |
| [deadpan] | Speaker speaks with no emotional expression | Styles |
| [melodic] | Speaker speaks with musical intonation | Styles |
| [harsh] | Speaker speaks with rough vocal quality | Styles |
| [gentle] | Speaker speaks softly and kindly | Styles |
| [commanding] | Speaker speaks with authoritative tone | Styles |
| [pleading] | Speaker speaks in begging manner | Styles |
| [persuasive] | Speaker speaks convincingly | Styles |
| [assertive] | Speaker speaks confidently and firmly | Styles |
| [tentative] | Speaker speaks hesitantly | Styles |
| [confident] | Speaker speaks with self-assurance | Styles |
| [nervous] | Speaker speaks with anxiety | Styles |
| [relaxed] | Speaker speaks in calm manner | Styles |
| [tense] | Speaker speaks with strain | Styles |
| [flowing] | Speaker speaks with smooth continuity | Styles |
| [halting] | Speaker speaks with frequent stops | Styles |
| [explosive] | Speaker speaks with sudden bursts | Styles |
| [controlled] | Speaker speaks with restraint | Styles |
| [wild] | Speaker speaks without restraint | Styles |
| [precise] | Speaker speaks with exact pronunciation | Styles |
| [sloppy] | Speaker speaks carelessly | Styles |
| [professional] | Speaker uses business-like delivery | Styles |
| [intimate] | Speaker speaks closely and personally | Styles |
| [distant] | Speaker speaks with emotional distance | Styles |
| [warm] | Speaker speaks with friendly warmth | Styles |
| [cold] | Speaker speaks without warmth | Styles |
| [mechanical] | Speaker speaks like a machine | Styles |
| [human] | Speaker speaks naturally and warmly | Styles |
| [robotic] | Speaker speaks with artificial quality | Styles |
| [organic] | Speaker speaks naturally | Styles |
| [stilted] | Speaker speaks awkwardly and unnaturally | Styles |
| [natural] | Speaker speaks effortlessly | Styles |
| [forced] | Speaker speaks with obvious effort | Styles |
| [effortless] | Speaker speaks with ease | Styles |
| [labored] | Speaker speaks with difficulty | Styles |
| [fluid] | Speaker speaks with smooth flow | Styles |
| [jerky] | Speaker speaks with uneven rhythm | Styles |
| [polished] | Speaker speaks with refined delivery | Styles |
| [rough] | Speaker speaks with unrefined quality | Styles |
| [eloquent] | Speaker speaks with beautiful expression | Styles |
| [stammering] | Speaker speaks with repeated sounds | Styles |
| [stuttering] | Speaker speaks with speech impediment | Styles |
| [lisping] | Speaker speaks with lisp | Styles |
| [slurring] | Speaker speaks with unclear articulation | Styles |
| [enunciating] | Speaker speaks with clear pronunciation | Styles |
| [projecting] | Speaker speaks to reach large audience | Styles |
| [intimate whisper] | Speaker whispers intimately | Styles |
| [stage whisper] | Speaker whispers theatrically | Styles |
| [bellowing] | Speaker speaks very loudly | Styles |
| [booming] | Speaker speaks with resonant volume | Styles |
| [squeaking] | Speaker speaks with high thin voice | Styles |
| [croaking] | Speaker speaks with rough low voice | Styles |
| [purring] | Speaker speaks with smooth low tone | Styles |
| [chirping] | Speaker speaks with light quick tone | Styles |
| [droning] | Speaker speaks monotonously | Styles |
| [chanting] | Speaker speaks in rhythmic repetition | Styles |
| [sing-song] | Speaker speaks with musical ups and downs | Styles |
| [lilting] | Speaker speaks with rising and falling tone | Styles |
| [cadenced] | Speaker speaks with regular rhythm | Styles |
| [syncopated] | Speaker speaks with irregular rhythm | Styles |
| [pulsing] | Speaker speaks with rhythmic beats | Styles |
| [pounding] | Speaker speaks with heavy emphasis | Styles |
| [tapping] | Speaker speaks with light rhythm | Styles |
| [bouncing] | Speaker speaks with lively rhythm | Styles |
| [swinging] | Speaker speaks with jazz-like rhythm | Styles |
| [marching] | Speaker speaks with military rhythm | Styles |
| [waltzing] | Speaker speaks with 3/4 time rhythm | Styles |
| [improvised] | Speaker speaks spontaneously | Styles |
| [rehearsed] | Speaker speaks with practiced delivery | Styles |
| [scripted] | Speaker reads from written text | Styles |
| [ad-libbed] | Speaker speaks without preparation | Styles |
| [extemporaneous] | Speaker speaks off the cuff | Styles |
| [spontaneous] | Speaker speaks without planning | Styles |
| [calculated] | Speaker speaks with planned intent | Styles |
| [strategic] | Speaker speaks with purpose | Styles |
| [tactical] | Speaker speaks with specific goal | Styles |
| [diplomatic] | Speaker speaks carefully and tactfully | Styles |
| [blunt] | Speaker speaks directly without tact | Styles |
| [evasive] | Speaker speaks to avoid direct answers | Styles |
| [direct] | Speaker speaks straightforwardly | Styles |
| [circuitous] | Speaker speaks in roundabout way | Styles |
| [straightforward] | Speaker speaks simply and clearly | Styles |
| [complicated] | Speaker speaks in complex manner | Styles |
| [simple] | Speaker speaks in basic terms | Styles |
| [sophisticated] | Speaker speaks with refinement | Styles |
| [crude] | Speaker speaks roughly | Styles |
| [refined] | Speaker speaks with elegance | Styles |
| [cultured] | Speaker speaks with education | Styles |
| [uncultured] | Speaker speaks without refinement | Styles |
| [educated] | Speaker speaks with learning | Styles |
| [street-smart] | Speaker speaks with urban wisdom | Styles |
| [academic] | Speaker speaks with scholarly tone | Styles |
| [colloquial] | Speaker uses everyday language | Styles |
| [vernacular] | Speaker uses local speech patterns | Styles |
| [slang] | Speaker uses informal language | Styles |
| [proper] | Speaker uses correct formal language | Styles |
| [grammatical] | Speaker speaks with correct grammar | Styles |
| [ungrammatical] | Speaker speaks with poor grammar | Styles |
| [poetic] | Speaker speaks with lyrical quality | Styles |
| [prosaic] | Speaker speaks in ordinary manner | Styles |
| [lyrical] | Speaker speaks with song-like quality | Styles |
| [narrative] | Speaker speaks in storytelling style | Styles |
| [descriptive] | Speaker speaks with vivid details | Styles |
| [analytical] | Speaker speaks with logical analysis | Styles |
| [emotional] | Speaker speaks with feeling | Styles |
| [factual] | Speaker speaks with just facts | Styles |
| [opinionated] | Speaker speaks with strong views | Styles |
| [neutral] | Speaker speaks without bias | Styles |
| [partisan] | Speaker speaks with clear bias | Styles |
| [objective] | Speaker speaks impartially | Styles |
| [subjective] | Speaker speaks from personal view | Styles |
| [fast] | Quick speaking pace | Rhythm |
| [rushed] | Hurried, urgent delivery | Rhythm |
| [hurried] | Fast-paced with anxiety | Rhythm |
| [breathless] | Out of breath, rapid speech | Rhythm |
| [faster] | Increasing speed | Rhythm |
| [speedy] | Very quick delivery | Rhythm |
| [quick] | Brief, fast responses | Rhythm |
| [lightning pace] | Extremely rapid speech | Rhythm |
| [slow] | Deliberately slow pace | Rhythm |
| [dragging] | Overly slow, labored | Rhythm |
| [sluggish] | Heavy, slow delivery | Rhythm |
| [leisurely] | Relaxed, unhurried pace | Rhythm |
| [measured] | Careful, controlled timing | Rhythm |
| [steady] | Consistent, even pace | Rhythm |
| [calculated] | Precise, deliberate timing | Rhythm |
| [paused] | With deliberate breaks | Rhythm |
| [pauses] | Strategic silence moments | Rhythm |
| [beat] | Rhythmic pulse timing | Rhythm |
| [dramatic pause] | Extended pauses for emphasis | Rhythm |
| [silence] | Complete quiet moments | Rhythm |
| [casual pause] | Natural, relaxed breaks | Rhythm |
| [long pause] | Extended silence | Rhythm |
| [short pause] | Brief hesitation | Rhythm |
| [halting] | Stopping and starting | Rhythm |
| [stammer] | Repetitive speech blocks | Rhythm |
| [stammers] | Multiple speech hesitations | Rhythm |
| [stutter] | Involuntary speech repetition | Rhythm |
| [stuttering] | Ongoing speech disruption | Rhythm |
| [slurred] | Unclear, blended words | Rhythm |
| [mumbled] | Indistinct, quiet speech | Rhythm |
| [run-on] | Continuous without breaks | Rhythm |
| [cut-off] | Abruptly interrupted | Rhythm |
| [cut-off mid-sentence] | Stopped while speaking | Rhythm |
| [trail off] | Gradually fading away | Rhythm |
| [trailing off] | Voice diminishing | Rhythm |
| [faint] | Barely audible delivery | Rhythm |
| [drifting] | Unfocused, wandering pace | Rhythm |
| [swayed] | Gently rocking rhythm | Rhythm |
| [hesitant] | Uncertain, cautious timing | Rhythm |
| [uncertain] | Doubtful delivery pace | Rhythm |
| [confident rhythm] | Assured timing pattern | Rhythm |
| [syncopated] | Off-beat rhythm pattern | Rhythm |
| [off-beat] | Unexpected timing | Rhythm |
| [jazzy rhythm] | Musical, improvised flow | Rhythm |
| [chain-pushed] | Connected, flowing words | Rhythm |
| [legato] | Smooth, connected delivery | Rhythm |
| [staccato] | Sharp, detached words | Rhythm |
| [rhythmic] | Patterned, musical flow | Rhythm |
| [tempo up] | Accelerating pace | Rhythm |
| [tempo down] | Decelerating pace | Rhythm |
| [accelerando] | Gradually faster | Rhythm |
| [ritardando] | Gradually slower | Rhythm |
| [brevity] | Concise, short delivery | Rhythm |
| [expansive] | Drawn-out, extended | Rhythm |
| [understatement] | Subtle, restrained timing | Rhythm |
| [overstatement] | Exaggerated timing | Rhythm |
| [ironic rhythm] | Contradictory pace | Rhythm |
| [fluid] | Smooth, flowing delivery | Rhythm |
| [choppy] | Uneven, broken flow | Rhythm |
| [stop-start] | Interrupted rhythm | Rhythm |
| [dramatic timing] | Theatrical pacing | Rhythm |
| [comedy timing] | Humorous pause placement | Rhythm |
| [deadpan timing] | Flat, emotionless pace | Rhythm |
| [quick fire] | Rapid succession | Rhythm |
| [pique pause] | Curiosity-building break | Rhythm |
| [question pause] | Inquiry hesitation | Rhythm |
| [exclamation pause] | Emphasis break | Rhythm |
| [breath orders] | Breathing pattern control | Rhythm |
| [stress pause] | Tension-filled silence | Rhythm |
| [pulse beat] | Heartbeat-like rhythm | Rhythm |
| [robotic] | Mechanical, artificial timing | Rhythm |
| [natural flow] | Organic speech pattern | Rhythm |
| [conversational] | Casual dialogue pace | Rhythm |
| [narrative] | Storytelling rhythm | Rhythm |
| [urgent] | Pressing, immediate pace | Rhythm |
| [melodic] | Musical speech pattern | Rhythm |
| [monotone] | Single-tone delivery | Rhythm |
| [varied pace] | Changing speed patterns | Rhythm |
| [consistent pace] | Steady, unchanging | Rhythm |
| [building tension] | Escalating intensity | Rhythm |
| [release tension] | Relaxing intensity | Rhythm |
| [punchy] | Sharp, impactful delivery | Rhythm |
| [smooth flow] | Effortless continuity | Rhythm |
| [bouncy] | Energetic, lively rhythm | Rhythm |
| [floating] | Light, airy delivery | Rhythm |
| [pulsing] | Throbbing rhythm pattern | Rhythm |
| [wave-like] | Undulating pace | Rhythm |
| [elastic] | Flexible timing | Rhythm |
| [organic] | Natural rhythm variation | Rhythm |
| [gasp] | Sharp intake of breath | Vocal Effects |
| [gulp] | Swallowing sound | Vocal Effects |
| [sigh] | Exhaled breath expression | Vocal Effects |
| [heavy sigh] | Deep, weary exhale | Vocal Effects |
| [breathy sigh] | Soft, whispered exhale | Vocal Effects |
| [sob] | Crying sound | Vocal Effects |
| [sobs] | Multiple crying sounds | Vocal Effects |
| [cry] | Emotional weeping | Vocal Effects |
| [tear up] | Beginning to cry | Vocal Effects |
| [wail] | Loud, mournful cry | Vocal Effects |
| [laugh] | Joyful vocal expression | Vocal Effects |
| [chuckle] | Quiet, soft laugh | Vocal Effects |
| [giggle] | Light, playful laugh | Vocal Effects |
| [snort] | Nasal laugh sound | Vocal Effects |
| [cackle] | Wild, harsh laugh | Vocal Effects |
| [titter] | Nervous, restrained laugh | Vocal Effects |
| [belch] | Burping sound | Vocal Effects |
| [cough] | Throat clearing sound | Vocal Effects |
| [cough soft] | Gentle throat clear | Vocal Effects |
| [cough hack] | Harsh, rough cough | Vocal Effects |
| [pant] | Quick, shallow breathing | Vocal Effects |
| [panting] | Rapid breathing pattern | Vocal Effects |
| [gasping] | Struggling for air | Vocal Effects |
| [yawn] | Tired, sleepy sound | Vocal Effects |
| [hum] | Melodic vocal tone | Vocal Effects |
| [hmm] | Thoughtful expression | Vocal Effects |
| [murmur] | Low, indistinct sound | Vocal Effects |
| [mumble] | Unclear, muffled speech | Vocal Effects |
| [whispered breath] | Soft, breathy whisper | Vocal Effects |
| [shriek] | High-pitched scream | Vocal Effects |
| [moaning] | Low, pained sound | Vocal Effects |
| [whining] | Complaining vocal tone | Vocal Effects |
| [grunt] | Short, rough sound | Vocal Effects |
| [groan] | Deep, strained sound | Vocal Effects |
| [clucking tongue] | Disapproving click | Vocal Effects |
| [click tongue] | Sharp tongue sound | Vocal Effects |
| [tongue roll] | Rolling tongue trill | Vocal Effects |
| [lick lips] | Lip moistening sound | Vocal Effects |
| [chew] | Eating, chewing sound | Vocal Effects |
| [burp] | Stomach gas release | Vocal Effects |
| [fart] | Bodily gas sound | Vocal Effects |
| [snore] | Sleeping breath sound | Vocal Effects |
| [clears throat] | Preparatory throat clear | Vocal Effects |
| [cough clear] | Clearing cough | Vocal Effects |
| [breath hold] | Suspended breathing | Vocal Effects |
| [heavy breathing] | Labored respiration | Vocal Effects |
| [wheeze] | Whistling breath sound | Vocal Effects |
| [growl] | Low, threatening sound | Vocal Effects |
| [roar] | Loud, powerful shout | Vocal Effects |
| [whimper] | Soft, pitiful sound | Vocal Effects |
| [laugh track] | Artificial audience laughter | Vocal Effects |
| [applause] | Clapping audience | Vocal Effects |
| [cheers] | Celebratory crowd noise | Vocal Effects |
| [boo] | Disapproval crowd sound | Vocal Effects |
| [laugh wry] | Sarcastic, dry laugh | Vocal Effects[[ |
| [laugh evil] | Menacing, dark laugh | Vocal Effects |
| [laugh nervous] | Anxious, uncertain laugh | Vocal Effects |
| [laugh joyful] | Happy, genuine laugh | Vocal Effects |
| [yelp] | Sharp, surprised cry | Vocal Effects |
| [ohh] | Wonder or realization | Vocal Effects |
| [ahh] | Understanding or relief | Vocal Effects |
| [ooh] | Impressed exclamation | Vocal Effects |
| [eh] | Questioning or dismissive | Vocal Effects |
| [hmm!] | Surprised consideration | Vocal Effects |
| [uh-oh] | Concern or mistake | Vocal Effects |
| [aha] | Discovery or understanding | Vocal Effects |
| [yip] | Quick, excited sound | Vocal Effects |
| [gah] | Frustration exclamation | Vocal Effects |
| [eek] | Frightened squeal | Vocal Effects |
| [bleep] | Censoring sound | Vocal Effects |
| [beep] | Electronic tone | Vocal Effects |
| [rattle] | Shaking, vibrating sound | Vocal Effects |
| [screech] | High-pitched harsh sound | Vocal Effects |
| [thud] | Heavy impact sound | Vocal Effects |
| [clang] | Metallic collision sound | Vocal Effects |
| [clap] | Hand striking sound | Vocal Effects |
| [snap] | Quick finger click | Vocal Effects |
| [tap] | Light striking sound | Vocal Effects |
| [twitch] | Sudden movement sound | Vocal Effects |
| [squeak] | High-pitched friction sound | Vocal Effects |
| [hiccup] | Involuntary diaphragm spasm | Vocal Effects |
| [hiccups] | Repeated hiccup sounds | Vocal Effects |
| [sniff] | Nasal inhalation | Vocal Effects |
| [sniffle] | Congested nose sound | Vocal Effects |
| [snort laugh] | Nasal laugh burst | Vocal Effects |
| [whistle] | Pursed lip tone | Vocal Effects |
| [kiss] | Lip smacking sound | Vocal Effects |
| [pucker] | Lip pursing sound | Vocal Effects |
| [slurp] | Liquid drinking sound | Vocal Effects |
| [gargle] | Throat liquid sound | Vocal Effects |
| [choking] | Airway obstruction sound | Vocal Effects |
| [gag] | Throat reflex sound | Vocal Effects |
| [retch] | Nausea reaction sound | Vocal Effects |
| [shush] | Quiet gesture sound | Vocal Effects |
| [psst] | Attention-getting whisper | Vocal Effects |
| [tsk] | Disapproval click | Vocal Effects |
| [wow] | Amazement exclamation | Vocal Effects |
| [whoa] | Surprise or caution | Vocal Effects |
| [heh] | Mild amusement | Vocal Effects |
| [pfft] | Dismissive sound | Vocal Effects |
| [brr] | Cold shivering sound | Vocal Effects |
| [achoo] | Sneeze sound | Vocal Effects |
| [bless you] | Sneeze response | Vocal Effects |
| [oops] | Mistake acknowledgment | Vocal Effects |
| [doh] | Frustrated realization | Vocal Effects |
| [meh] | Indifferent expression | Vocal Effects |
| [blah] | Disgust or boredom | Vocal Effects |
| [ugh] | Annoyance or effort | Vocal Effects |
| [phew] | Relief or exhaustion | Vocal Effects |
| [tada] | Celebration sound | Vocal Effects |
| [voila] | Presentation exclamation | Vocal Effects |
| [ahem] | Attention-getting cough | Vocal Effects |
| [shh] | Silencing gesture | Vocal Effects |
| [mmm] | Satisfaction or thought | Vocal Effects |
| [nom nom] | Eating enjoyment | Vocal Effects |
| [yum] | Taste appreciation | Vocal Effects |
| [yuck] | Disgust reaction | Vocal Effects |
| [eww] | Revulsion sound | Vocal Effects |
| [ick] | Disgust expression | Vocal Effects |
| [ouch] | Pain reaction | Vocal Effects |
| [ow] | Sharp pain sound | Vocal Effects |
| [oww] | Extended pain cry | Vocal Effects |
| [yeehaw] | Excitement celebration | Vocal Effects |
| [yahoo] | Joyful exclamation | Vocal Effects |
| [hooray] | Victory cheer | Vocal Effects |
| [boo-hoo] | Crying sound | Vocal Effects |
| [snicker] | Suppressed laugh | Vocal Effects |
| [chortle] | Gleeful chuckle | Vocal Effects |
| [guffaw] | Loud, hearty laugh | Vocal Effects |
| [happy] | Joyful, positive mood | Emotion |
| [joyful] | Pure happiness and delight | Emotion |
| [content] | Satisfied, peaceful state | Emotion |
| [peaceful] | Calm, tranquil feeling | Emotion |
| [optimistic] | Hopeful, positive outlook | Emotion |
| [cheerful] | Bright, upbeat mood | Emotion |
| [blissful] | Pure joy and serenity | Emotion |
| [grateful] | Thankful, appreciative | Emotion |
| [relieved] | Free from worry | Emotion |
| [satisfied] | Fulfilled, pleased | Emotion |
| [excited] | Energetic enthusiasm | Emotion |
| [eager] | Keen anticipation | Emotion |
| [anticipatory] | Expectant, waiting | Emotion |
| [enthusiastic] | Passionate excitement | Emotion |
| [thrilled] | Extremely excited | Emotion |
| [proud] | Dignified satisfaction | Emotion |
| [confident] | Self-assured, certain | Emotion |
| [resolute] | Determined, unwavering | Emotion |
| [brave] | Courageous, fearless | Emotion |
| [courageous] | Bold, heroic | Emotion |
| [calm] | Peaceful, untroubled | Emotion |
| [serene] | Tranquil, composed | Emotion |
| [trusting] | Having faith in others | Emotion |
| [trustworthy] | Reliable, dependable tone | Emotion |
| [caring] | Compassionate, loving | Emotion |
| [compassionate] | Empathetic, understanding | Emotion |
| [nurturing] | Protective, supportive | Emotion |
| [romantic] | Loving, intimate | Emotion |
| [passionate] | Intense, fervent | Emotion |
| [adoring] | Deeply loving | Emotion |
| [sensitive] | Gentle, considerate | Emotion |
| [tender] | Soft, affectionate | Emotion |
| [sincere] | Genuine, honest | Emotion |
| [honest] | Truthful, straightforward | Emotion |
| [gentle] | Kind, mild-mannered | Emotion |
| [melancholic] | Sad, reflective | Emotion |
| [sad] | Sorrowful, unhappy | Emotion |
| [heartbroken] | Deeply hurt, devastated | Emotion |
| [depressed] | Low, dejected mood | Emotion |
| [lonely] | Isolated, longing | Emotion |
| [irritated] | Mildly annoyed | Emotion |
| [annoyed] | Bothered, vexed | Emotion |
| [frustrated] | Blocked, hindered feeling | Emotion |
| [angry] | Hostile, upset | Emotion |
| [rageful] | Intensely angry | Emotion |
| [furious] | Violently angry | Emotion |
| [jealous] | Envious, possessive | Emotion |
| [envious] | Wanting what others have | Emotion |
| [resentful] | Bitter, indignant | Emotion |
| [bitter] | Harsh, resentful | Emotion |
| [skeptical] | Doubtful, questioning | Emotion |
| [doubtful] | Uncertain, hesitant | Emotion |
| [cynical] | Distrustful, pessimistic | Emotion |
| [suspicious] | Wary, distrustful | Emotion |
| [anxious] | Worried, uneasy | Emotion |
| [nervous] | Tense, apprehensive | Emotion |
| [apprehensive] | Fearful anticipation | Emotion |
| [tense] | Stressed, on edge | Emotion |
| [fearful] | Afraid, scared | Emotion |
| [terrified] | Extremely frightened | Emotion |
| [shocked] | Stunned, startled | Emotion |
| [surprised] | Unexpected reaction | Emotion |
| [startled] | Suddenly alarmed | Emotion |
| [confused] | Uncertain, bewildered | Emotion |
| [puzzled] | Perplexed, mystified | Emotion |
| [curious] | Inquisitive, interested | Emotion |
| [inquisitive] | Eager to learn | Emotion |
| [pensive] | Thoughtful, reflective | Emotion |
| [contemplative] | Deep in thought | Emotion |
| [thoughtful] | Considerate, reflective | Emotion |
| [wistful] | Yearning, nostalgic | Emotion |
| [nostalgic] | Longing for the past | Emotion |
| [longing] | Deep desire, yearning | Emotion |
| [embarrassed] | Self-conscious, awkward | Emotion |
| [ashamed] | Guilt, regret | Emotion |
| [guilty] | Remorseful, responsible | Emotion |
| [remorseful] | Regretful, apologetic | Emotion |
| [hopeful] | Optimistic expectation | Emotion |
| [realistic] | Practical, grounded | Emotion |
| [playful] | Fun-loving, mischievous | Emotion |
| [mischievous] | Playfully naughty | Emotion |
| [sarcastic] | Ironically mocking | Emotion |
| [witty] | Cleverly humorous | Emotion |
| [amused] | Entertained, pleased | Emotion |
| [delighted] | Highly pleased | Emotion |
| [ecstatic] | Overwhelmingly happy | Emotion |
| [elated] | Extremely happy | Emotion |
| [euphoric] | Intensely joyful | Emotion |
| [jubilant] | Triumphantly joyful | Emotion |
| [motivated] | Driven, inspired | Emotion |
| [inspired] | Creatively energized | Emotion |
| [determined] | Resolute, focused | Emotion |
| [focused] | Concentrated, attentive | Emotion |
| [serious] | Grave, solemn | Emotion |
| [solemn] | Formal, dignified | Emotion |
| [stern] | Strict, severe | Emotion |
| [authoritative] | Commanding respect | Emotion |
| [commanding] | Powerful, controlling | Emotion |
| [dominant] | Assertive, controlling | Emotion |
| [submissive] | Yielding, compliant | Emotion |
| [vulnerable] | Exposed, defenseless | Emotion |
| [fragile] | Delicate, easily hurt | Emotion |
| [resilient] | Strong, adaptable | Emotion |
| [stoic] | Emotionally restrained | Emotion |
| [indifferent] | Uncaring, neutral | Emotion |
| [apathetic] | Lacking interest | Emotion |
| [bored] | Uninterested, weary | Emotion |
| [tired] | Weary, exhausted | Emotion |
| [energetic] | Full of energy | Emotion |
| [vibrant] | Lively, dynamic | Emotion |
| [dramatic] | Theatrical, intense | Emotion |
| [mysterious] | Enigmatic, secretive | Emotion |
| [seductive] | Alluring, enticing | Emotion |
| [flirtatious] | Playfully romantic | Emotion |
| [sultry] | Sensually appealing | Emotion |
| [innocent] | Pure, naive | Emotion |
| [naive] | Inexperienced, trusting | Emotion |
| [wise] | Knowledgeable, sage | Emotion |
| [mature] | Grown-up, developed | Emotion |
| [childlike] | Innocent, playful | Emotion |
| [rebellious] | Defiant, nonconformist | Emotion |
| [defiant] | Boldly resistant | Emotion |
| [stubborn] | Obstinate, unyielding | Emotion |
| [patient] | Tolerant, enduring | Emotion |
| [impatient] | Restless, eager | Emotion |
| [tolerant] | Accepting, open-minded | Emotion |
| [intolerant] | Unwilling to accept | Emotion |
| [humble] | Modest, unassuming | Emotion |
| [arrogant] | Conceited, superior | Emotion |
| [modest] | Unassuming, humble | Emotion |
| [vain] | Conceited, self-absorbed | Emotion |
Note: These tags are most effective when used thoughtfully—proper phrasing, punctuation, and the right voice setting (Creative or Natural stability) significantly enhance performance. For best results, test tags within longer prompts (over ~250 characters) and match tags to voices that support them.
ElevenLabs v3 Audio Tag Tool
Experience the power of ElevenLabs v3 Alpha with our intelligent audio tag generator. Simply paste your text below, and our AI will analyze the emotional content, character dynamics, and delivery requirements to automatically add professional-grade audio tags that bring your words to life.
Whether you’re creating audiobooks, YouTube content, podcasts, or marketing materials, this tool optimizes your scripts for maximum emotional impact using ElevenLabs v3’s revolutionary audio tag system. No more guessing which tags to use – get expert-level emotional direction in seconds.
Perfect for: Content creators, voice artists, marketers, educators, and anyone wanting to harness the full expressive power of AI voices.
Your optimized text will appear here
Choosing the Right Voice for Eleven v3
Eleven v3 features three stability modes: Creative Mode maximizes emotional expression and tag responsiveness for character work and entertainment; Natural Mode balances expression with consistency for most general applications; and Robust Mode prioritizes consistency for professional and corporate content. Note that Professional Voice Clones are not yet fully optimized for v3.
| Content Type | Recommended Voice Characteristics | Optimal Settings | Tag Responsiveness |
|---|---|---|---|
| Audiobook Narration | Neutral clear consistent | Natural mode medium stability | High |
| Character Dialogue | Expressive distinctive | Creative mode lower stability | Very High |
| Corporate Content | Professional authoritative | Robust mode high stability | Medium |
| Educational Material | Clear engaging patient | Natural mode medium stability | High |
| Entertainment/Comedy | Dynamic flexible animated | Creative mode low stability | Exceptional |
| News/Journalism | Credible clear measured | Robust mode high stability | Medium |
Note: Creative Mode offers maximum expression and tag responsiveness but may require more prompt engineering due to occasional variations. Natural Mode provides the optimal balance for most applications. Robust Mode ensures maximum consistency similar to v2 but with reduced emotional range. Professional Voice Clones (PVCs) are not yet fully optimized for v3 – use Instant Voice Clones (IVCs) or designed voices for best results.
Best Practices
- Placement matters: Insert tags at the point in the text where you want the effect to start. Tags typically influence the delivery of the words that come after them (until perhaps a contrasting tag appears or the sentence ends). If you put [shouting] at the beginning of a sentence, the whole sentence will likely be shouted. If you put it in the middle, the voice might raise volume from that point onward.
- Voice-dependent effectiveness: Not every voice in the ElevenLabs library will respond equally to every tag. Some synthetic voices are better at certain expressions than others. For example, a very soft-spoken voice might not handle a [shouts] tag convincingly, and a voice that was cloned from neutral narration might not have an expressive laugh. The developers note that the tag effectiveness is somewhat voice and context dependent elevenlabs.io . It’s wise to test your chosen voice with a variety of tags to understand its range. In many cases you might select or design a voice that matches the emotional range you need (e.g., a voice that already has a hint of playfulness will likely do better with [giggles] or [mischievously] tags).
- Context and wording: The model also infers emotion from the surrounding text, not just the tags. Descriptive language like “he said excitedly” or an exclamation point can naturally make the voice more excited elevenlabs.io . Audio tags are a more direct way to force an effect, but you’ll get the most reliable results by aligning the tag with context. For instance, writing “No... please [crying] don’t go.” is better than just “No, please don’t go.” with a [crying] tag slapped on, because the first version provides context that matches the crying tone. A combination of tags and descriptive prompting yields the best performances.
- Use punctuation as tags’ ally: Punctuation plays a big role in ElevenLabs v3 outputs. An ellipsis (...) will cause a pause or trailing off, which can amplify a sad or dramatic moment. Commas and periods ensure the voice takes natural breaths. An exclamation mark conveys excitement or shouting. Writing in ALL CAPS can even signal emphasis or loudness for a word elevenlabs.io . For example, “I said NOW!” will emphasize “now” more than “I said now.” would. You can leverage this along with tags: “I said [shouting] NOW!” to really drive the point home. Don’t underestimate how important good punctuation and capitalization are in sculpting the delivery – they work hand in hand with the tags to produce life-like speech.
- Discovering new tags: While the documentation provides many tags, it’s not an exhaustive list of everything the model can understand. Users are experimenting with making up their own tags or using synonyms. The model might interpret [groans] or [grunting] even if not officially listed, for example. The advice is to experiment with descriptive terms in brackets – you might stumble on additional styles or sounds. The v3 model is quite flexible and was trained on a wide array of audio patterns, so creative prompting can yield interesting results elevenlabs.io . Just be sure to test thoroughly, especially if you plan to use a less common tag in production, as consistency can vary.
Eleven v3 Examples
4 Videos
Tag Basics: Quick Start Guide
Audio tags work like stage directions for AI voices. Simply wrap instructions in brackets [like this] within your text to control delivery, emotion, and environment. Here are the three core ways to use them:
Key Applications:
- Emotional Delivery: "This is a bad idea, [whispering] she thought [sighs]"
- Character Reactions: "Oh, that's rich! [laughing] You really think I'd tell you?"
- Environmental Sound: "I stepped inside [door creaks] as [thunder] rumbled overhead"
Complete Scene Examples
Ready to see tags in action? These 10 copyable examples demonstrate professional techniques across different genres. Each includes a playable audio preview so you can hear exactly how the tags transform the delivery.
Thriller Scene
Romantic Comedy
[cafe ambient] Mark fidgeted with his coffee cup.
[stammering] "So, um, I was wondering if maybe..."
[giggle fit] She couldn't help but laugh at his adorable nervousness.
[playful banter] "Are you asking me out, or ordering a sandwich?"
[self-deprecating chuckle] "Definitely the worst pickup line in history."
[warm] "I'd love to go out with you, Mark."
Fantasy Adventure
Horror Story
Business Presentation
[office ambient] [professional] [confident] Good morning, everyone.
[mouse click] Let's review our Q4 results.
[enthusiastic] I'm excited to announce a 35% increase in revenue!
[applause] [motivational tone] This success belongs to each and every one of you.
[projecting] Together, we're building something extraordinary.
Children's Bedtime Story
[whimsical] [storybook style] Once upon a time, in a magical forest...
[bird chirping] [gentle] Little Bunny hopped through the meadow.
[child narrator] "Where are you going?" asked the wise old owl.
[sing-song] "To find the rainbow flowers that grant wishes!"
[wind chimes] [sleepy] And they all lived happily ever after.
[yawning] The end.
Podcast Interview
[podcast host] [conversational] Welcome back to Tech Talk Tuesday!
[upbeat] Today we're speaking with AI researcher Dr. Johnson.
[professional] "Thank you for having me on the show."
[curious] "Tell us about your latest breakthrough in neural networks."
[articulate] [excited] "Well, we've discovered something fascinating..."
Action Movie Scene
[car engine] [adrenaline] The chase was on!
[tires screeching] [radio static] "Backup needed on Fifth Street!"
[gunshot] [glass breaking] Bullets shattered the rear window.
[shouted reply] [determined] "Not today!"
[explosion] [helicopter] The bridge collapsed behind them.
[breathing heavily] [relieved] "That was too close."
Cooking Show
[kitchen ambient] [cheerful] [energetic] Welcome to Chef Maria's kitchen!
[sizzling] Today we're making the perfect risotto.
[knife chopping] First, dice the onions finely.
[bubble pop] [timer beep] Listen for that beautiful sizzle!
[tasting] [delighted] Mmm, absolutely divine!
[warm] [inspiring] Cooking is love made visible.
Emotional Drama
[hospital ambient] [vulnerable] She sat by his bedside, holding his hand.
[soft whisper] "Please wake up, Dad."
[sob break] The machines beeped steadily.
[reflective] [nostalgic] She remembered teaching her to ride a bike.
[hopeful] [trembling] "I'm not ready to say goodbye."
[squeeze] His fingers moved slightly.
[gasp] [tearful] "Dad? Can you hear me?"
As you can see, audio tags are a powerful tool for creative control. They allow you to inject emotion, personality, and ambiance directly into the script. Next, we’ll turn our attention to the multi-speaker dialogue capabilities of ElevenLabs v3, which take things a step further by letting you generate entire conversations.
Multi-Speaker Dialogue Generation
Another transformative feature of ElevenLabs v3 is its ability to generate multi-speaker dialogue. This means you can prompt the model with a script that includes multiple characters or speakers, each with their own voice, and get back one coherent audio file with all the voices interacting. For content creators, this opens up the possibility of creating fully-voiced scenes and conversations without recording multiple actors.
How does dialogue mode work?
In the ElevenLabs interface (or API), you can specify a dialogue by assigning lines of text to different voices. For example, you might label lines as Speaker A and Speaker B, choose a distinct AI voice for each, and then provide the conversation text. The model then weaves these voices together into a seamless exchange. Crucially, the voices are aware of each other in context – they share the scene’s context and emotional tone, leading to natural-sounding interactions. If one speaker asks a question with excitement, the other can reply in a matching emotional tone, and so on. The system pays attention to punctuation and tags for each speaker, ensuring things like interruptions and overlapping speech sound right.
Multi-Speaker Dialogue Examples
To illustrate, here’s what a simple dialogue prompt could look like in script form:
Alice: [nervous] Hey… I think we’re not alone here.
Bob: [whispering] I know. I heard something from the basement.
Alice: [shaken] This place gives me the creeps. [sighs] Maybe we should leave.
Bob: [firm] Not yet. We need to find out what’s going on.
In this prompt, “Alice” and “Bob” would each be assigned a different AI voice (say, a female voice for Alice and a male voice for Bob) in the ElevenLabs UI. The text includes tags like [nervous], [whispering], etc., to guide the emotion. The resulting audio would have Alice speaking her lines in a nervous tone, Bob replying in a hushed whisper, and so forth – effectively a mini audio drama scene generated in one go.
Eleven v3’s dialogue mode excels at handling things that make conversations feel real.
It supports interruptions and overlap – for instance, if one speaker’s line is cut off with an em dash (–) and the next speaker starts, the audio can reflect that interruption smoothly. In the example above, if Alice said “Maybe we should—” and Bob immediately interjected “—Not yet,” the model would output it with the timing of an actual interruption, rather than a hard stop and start. This ability to capture conversational timing quirks (like cutting in, pausing, trailing off) adds a lot of realism. Dialogue generation also maintains a consistent context across speakers.
The model essentially treats the whole conversation as one narrative thread. This means if earlier lines establish a mood or topic, later lines will reflect that. For example, if two characters are arguing in an angry tone, the model will likely keep both voices sounding tense throughout, unless a tag or a clear change in the text indicates a mood shift. This contextual continuity is a leap forward – it makes the AI voices respond to each other in a way that feels cohesive and meaningful, not like isolated monologues stuck together. ElevenLabs describes it as the system “matching prosody, emotional range and taking cues from audio tags” across the dialogue.
A key to making the most of dialogue mode is assigning the right voices to each character.
ElevenLabs offers a large voice library and also allows custom voices (through voice cloning or design). When creating a multi-speaker scene, you’ll want to pick voices that complement each other and fit the characters you have in mind. For instance, a scene with a teacher and a student might use an older-sounding authoritative voice for the teacher and a youthful voice for the student. Since v3 can handle many languages, you could even have characters speaking different languages to each other (for a bilingual scene) – the model will still keep the conversation flow natural. There is effectively no hard limit on the number of speakers you can include, so in theory you could script a roundtable discussion or a full-cast drama scene, though more complex scenes might require extra careful prompting (and possibly multiple generation attempts to get perfect).
From podcasts and radio plays to game dialogues and animated films, the multi-speaker capability is incredibly versatile. Content creators can prototype scenes with multiple characters without hiring voice actors for each role, which is great for pre-production and indie projects. Even for finished products like audiobooks, one narrator could generate dialogues for all the characters by leveraging this feature, giving the impression of a full voice cast. It’s worth noting that as of now, dialogue mode is exclusive to the ElevenLabs v3 model – you won’t find this in the older models. And because v3 is an alpha release, using dialogue mode might require a bit of trial and error (you might need to refine tags or punctuation to get the timing just right).
But the results can be stunning. An example from ElevenLabs’ own showcase has two AI voices joking about how much better v3 is, complete with one laughing and the other responding with amazement – and it truly sounds like two people bantering, with no robotic feel at all.
In summary, the dialogue generation feature turns ElevenLabs v3 into a text-to-dialogue system, not just text-to-speech.
It’s like having a virtual voice studio where you can script interactions between characters and hear them performed instantly. This drastically reduces the friction for creators to produce conversational content. Next, let’s consider some real-world use cases where these capabilities shine, and how different creative fields can leverage Eleven v3.
Practical Use Cases for Eleven v3
The advanced features of ElevenLabs v3 unlock a wide array of applications across different domains. Here are some of the most promising use cases and how v3 adds value in each:
- Podcasting and Audio Shows: Independent podcasters and audio drama creators can use v3 to generate high-quality narration and even character voices. For example, you might produce an entire fiction podcast episode with multiple characters voiced by the AI, each with distinct personalities. The dialogue mode means you can script out scenes and get a natural-sounding conversation, complete with emotions and timing. This lowers the barrier to creating full-cast dramas or interview-style shows when you don’t have multiple voice actors at hand. Even for non-fiction podcasts, v3 can be used to generate a crisp narration or intro in a desired style (serious, upbeat, etc.), or to voice quotes and excerpts in different accents and languages. The expressive voices ensure that the delivery keeps listeners engaged, which is crucial in audio-only content.
- Video Production and YouTube: For video creators, from YouTubers to indie filmmakers, ElevenLabs v3 is a boon for voiceovers. Narration for videos can be generated in minutes, saving the cost and time of recording voice talent. With the new audio tags, a video creator can imbue the narration with the right mood – for instance, a travel vlog voiceover could have a tone of awe and excitement, whereas a documentary might use a calm, informative style. By combining ElevenLabs TTS with video editing in Adobe Premiere Pro or After Effects (Audio Generation Extension integration soon), creators can streamline their workflow.
- Gaming and Interactive Media: Game developers and interactive storytellers can leverage ElevenLabs v3 to generate dialogue for NPCs (non-player characters), in-game narration, or even player character voices on the fly. Because v3’s voices are so lifelike and can express a range of emotions, they can make game interactions feel more immersive. Imagine a role-playing game where villagers greet you in different tones (happy, fearful, urgent) depending on the situation – these lines could be generated with tags like [happy] or [panicked] to reflect the context. For indie game devs who may not have budget for voice actors in many languages, v3 offers a way to have rich voice-acted content in English and beyond. Interactive fiction, VR experiences, and voice-based NPC dialogue trees all become more feasible. Moreover, the upcoming streaming support planned for v3 would be a game-changer for games – it could allow real-time generation of dialogue during gameplay (e.g., dynamic responses or commentary), once the technology matures.
- Audiobooks and Storytelling: Audiobook production is a natural fit for ElevenLabs v3. Traditionally, audiobooks require a narrator (or a full cast of voice actors for multi-character books), which is expensive and time-consuming to produce. With v3, an author or producer can generate an audiobook with a highly natural-sounding narrator voice that can convey the story’s emotions effectively. Using audio tags, different characters’ dialogue in the book can be given distinct delivery styles – a gruff [deep voice] for a dwarven character, a [soft-spoken] tone for a shy character, etc. The multi-speaker capability even allows you to have dialogues in the audiobook performed by multiple voices automatically, enhancing the listener’s experience.
- Education and E-Learning: Educators and e-learning content creators can use ElevenLabs v3 to generate engaging instructional audio. Dry material can be brought to life by using a slightly enthusiastic or conversational tone (via tags) to keep students attentive. For instance, an online course could have its lessons narrated in a friendly, encouraging voice that occasionally uses a [cheerful] tag when congratulating the learner or a [serious] tone when emphasizing an important point. Moreover, the multi-language support is invaluable for education – lessons can be delivered in the student’s native language, or language learning apps can demonstrate pronunciation in dozens of languages using the same platform.
These are just a few examples, but the possibilities are expansive. Essentially, any scenario where you need a voice – especially a voice that sounds human and can convey emotion – is a candidate for ElevenLabs v3’s technology. From voicemail systems and smart assistant voices to advertising and content creation, v3’s expressive AI voices can fill roles traditionally done by voice actors or narrators, or augment human voices in creative ways.
Crafting Effective Prompts
Because v3 offers so much control, the way you write your input prompt heavily influences the output. A general rule is to provide clear context and sufficient length in your prompts. Very short prompts (a few words or a single short sentence) may lead to inconsistent or abrupt outputs.
It’s recommended to use prompts longer than 250 characters for the best consistency. Introduce the scene or emotion through narration if needed, not just through tags.
Context Before Content
Always provide emotional and situational context before the actual dialogue:
❌ Poor: [angry] I can't believe you did that!
✅ Better: After discovering the betrayal, Sarah confronted her friend:
[angry] [hurt] I can't believe you did that to me! [voice breaking] I trusted you!
Introduce the scene or emotion through narration if needed, not just through tags. For example, instead of just writing “[angry] What are you doing here?”, you might write “She scowled and stepped forward, her voice low and angry. ‘[angry] What are you doing here?’”. This way, even without the tag, the model knows the character is angry from context – the tag then reinforces it. In general, combine natural language descriptions with tags for reliability. Also, be mindful of the ordering: describe who is speaking and how before the dialogue if possible (as in: John shouted, “Get out!” vs just “Get out!” with a [shouting] tag).
Emotional Journey Mapping
Plan the emotional arc of your content:
✅ Emotional Progression Example:
[nervous] I have something important to tell you... [pause]
[gathering courage] We've been friends for years, and... [deep breath]
[vulnerable] I think I'm falling in love with you. [nervous laugh]
[hopeful] Do you... do you feel the same way?
The choice of voice is critical with v3. ElevenLabs provides a variety of voices (both default voices and user-generated ones in the community library), and you can also create custom voices. Each voice has its own “personality” and will respond to tags in its own way.
For instance, a voice that was designed or trained on calm audiobook narration might have a narrower emotional range, whereas a voice created with diverse, expressive samples will handle dramatic tags better. The official guidance suggests including a broad emotional range when cloning or training voices for v3, because v3 is more expressive than v2 models were. If you find a certain tag isn’t yielding the effect you want, part of the reason could be the voice’s inherent style.
Character Voice Consistency
Develop voice profiles for each character:
Character Profile: Detective Morgan
- Base emotion: [serious] [analytical]
- Stress response: [intense] [focused]
- Humor style: [dry] [sarcastic]
- Vulnerability: [quiet] [reflective]
Example Usage:
Detective Morgan: [serious] The evidence doesn't lie. [pause]
[analytical] But people do. [dry humor] Funny how that works.
Don’t hesitate to try a different voice that is closer to the target delivery. For example, if you need a character to shout and laugh, pick a voice that has some natural energy or humor in its tone to begin with, as it will likely perform better with [shouts] or [laughs] cues.
On the flip side, if you need a very stable neutral narration, a neutral voice will be easier to keep consistent. The key is to match the voice to the role: a somber, deep voice for serious content, a bright friendly voice for upbeat content, etc. and then use tags to fine-tune within that range.
ElevenLabs v3 (Alpha) comes with a Stability slider (and related settings) that let you balance creativity versus consistency in output. This stability setting effectively controls how strictly the generation sticks to the average tone of the reference voice versus allowing more deviation for expressiveness. The slider often has modes like “Creative”, “Natural”, and “Robust” (as seen in the UI).
Layered Emotional Complexity
Combine multiple tags to create nuanced performances:
1. Conflicted Character:
[trying to sound confident but nervous] Everything's under control...
[forced laugh] [quieter] [worried] At least, I hope it is.
2. Gradual Emotional Shift:
[calm] I understand your concern. [slight irritation] But we've been over this.
[more frustrated] Multiple times. [angry] How many times do I need to explain?
3. Suppressed Emotion:
[controlled anger] [through gritted teeth] That's... [pause] [forced calm]
That's perfectly fine. [muttering] [sarcastic] Just wonderful.
Sample Scripts and Creative Examples
To spark your imagination, here are a few sample snippets showcasing ElevenLabs v3 in action. These examples demonstrate humorous, emotional, and dynamic scenes – all generated by carefully crafted text with audio tags.
Humorous Dialogue Example:
In this short comedic exchange, two characters banter with each other. One is telling a cheesy joke and the other is reacting with exasperation. Audio tags are used to inject laughter and sarcasm.
Alex: [smug] Hey, Tina, want to hear a construction joke?
Tina: [deadpan] Do I have a choice?
Alex: [excited] Oh, you are gonna love it. [clears throat] I'm still working on it! [laughs]
Tina: [groans] Ugh... That was terrible.
Alex: [laughing] Come on, that was funny!
Tina: [sarcastic] Sure, Alex. I'm laughing on the inside. [sighs heavily]
What’s happening: Alex’s lines use [smug] to sound self-satisfied and [excited] when delivering the punchline, followed by a [laughs] tag to actually laugh at his own joke. Tina’s responses use a [deadpan] tone (implied by her flat wording, even without an explicit tag) and then a [groans] to show frustration, and finally [sarcastic] and a heavy sigh to convey her mock laughter. The resulting audio would sound like a classic comic timing routine, with Tina’s dry delivery playing off Alex’s goofy enthusiasm. The tags make Alex audibly laugh and Tina audibly sigh, enhancing the humor.
Emotional Scene Example:
This example shows an emotional monologue where a character says goodbye. Tags help convey choked-up feelings and tears.
Emma: [tearful] I... I just wanted to say thank you, for everything. [voice breaks][sniffles] You have been like a sister to me, and I don't know how to do this goodbye.
What’s happening: The [tearful] tag at the start will make Emma’s voice sound like she’s on the verge of crying. Then “I… I just wanted to say” has those ellipses which cause slight pauses, as if she’s struggling to speak. The text [voice breaks] isn’t a standard tag, but written like this, the model might interpret it as an instruction to make the voice break or falter (one could also try [crying] here). [sniffles] is another directive that should produce a brief sniffle sound or at least the sense of a sniff. The line, delivered with these cues, would come out trembling and heartfelt, likely tugging at the listener’s heartstrings. It’s a demonstration of how you can layer tags (tearful + voice breaks + sniffle) to paint a very specific emotional picture.
Dynamic Action Scene Example:
In this action-packed narration, we mix sound effect tags and excited tones to simulate a scene from an adventure or game.
Narrator: [fast pace] The hero dashed into the ancient temple, heart pounding.
[footsteps] Each step echoed in the halls.
Suddenly, a trap was triggered! [loud rumble][rocks crumbling]
Hero: [shouting] Watch out!
Narrator: [tense] The ceiling began to collapse, debris falling everywhere. [coughing] Dust filled the air as they sprinted for the exit.
What’s happening: The Narrator voice is set to a [fast pace] (you could also try [panicked] or simply rely on exclamation points) to make the delivery urgent. The [footsteps] tag inserts the sound of running footsteps echoing. When the trap triggers, [loud rumble] and [rocks crumbling] simulate the sound of the temple starting to collapse. The Hero’s line has a [shouting] tag so the warning comes out as a yell. Then the Narrator continues in a tense tone describing the collapse, and even uses a [coughing] tag to show the narrator coughing from dust (a creative use of mixing first-person style reaction in a third-person narration, which the model can handle). The combined output would be a mini audio drama: you’d hear the running, the rumble of rocks, a character shouting “Watch out!”, and the narrative tension in the voice as the escape unfolds. All of that purely from textual description with tags.
These examples barely scratch the surface of what you can do. Feel free to experiment with different genres – horror scenes with [whispers] and [evil laugh], sci-fi dispatches with [distorted radio] effects (possibly achieved with a combination of tags or voice filters), or even musical moments with [sings]. The key is that Eleven v3 can handle a script like a director reading stage directions, turning them into audio elements. Now that we’ve seen what v3 can do on the creative side, let’s discuss how it fits into real-world production workflows, particularly with popular tools that creators already use. In the next section, we’ll cover integration with Adobe software and how Eleven v3 can streamline content creation processes.
Integration with Adobe Tools and Creative Workflows
ElevenLabs v3 is a standalone AI service (accessible via web interface or API), but it’s most powerful when combined with the tools creators use every day. Adobe’s creative suite – Premiere Pro for video editing, After Effects for motion graphics, and Audition for audio editing – is widely used in content production. While these tools don’t natively support advanced TTS, integration via the Audio Generation Extension plugin seamlessly injects a “virtual voiceover artist” into the workflow.
Using ElevenLabs v3 with Premiere Pro (Video Editing):
Premiere Pro is often the final assembly point for video projects, where you bring together visuals, music, and voiceovers. To use v3 in this context, you would generate your narration or character dialogue on the ElevenLabs platform and download the audio file (for example, an MP3 or WAV). Then, in Premiere, you import that audio into your project and place it on the timeline just like you would any recorded voice clip. Adobe Premiere handles standard audio formats, so there’s no issue using ElevenLabs-generated audio. In practice, a good workflow might be:
- Prepare your script – write directly in the plugin panel or your script editor, adding audio tags for expression.
- Generate the audio – click “Generate” in the plugin, which runs the prompt through ElevenLabs v3 and returns a polished voice clip.
- Import into Premiere, After Effects or Audition – the plugin auto-inserts the voice clip onto your selected timeline track
- Sync and edit – trim silence, adjust volume, apply fades; ElevenLabs delivers clean, ready-to-use audio
- Mix with other audio – If you have background music or sound effects, mix those with the AI voiceover, ducking music under narration, etc., as you normally would.
- Effortless revisions – change your script inline, regenerate, and the plugin updates the timeline automatically. No need to re-sync from scratch—just slight trim if needed.
By integrating ElevenLabs via the Audio Generation Extension, you’ve created a voiceover studio inside the Adobe ecosystem—no switching apps, no manual importing, and maximum creative efficiency. Let me know if you’d like a step-by-step guide or screenshots for a tutorial!
Note: ElevenLabs v3 is currently not available via API, but the Audio Generation Plugin will support the new text-to-speech model as soon as it’s released.
Conclusion
Eleven v3 (Alpha) marks a significant milestone in text-to-speech technology. As we’ve explored, it’s not just an incremental improvement; it’s a reimagining of what AI-generated speech can do – from rich emotional expression with audio tags to multi-voice dialogues that sound like real conversations. This model empowers a wide range of users: content creators can produce high-quality voiceovers and character performances without a studio, educators and businesses can localize and enliven their content in 70+ languages, and developers can soon integrate these voices into applications for immersive user experiences.
The quality of output from Eleven v3 is, in many cases, astonishingly close to human speech. It captures nuances like tone shifts, laughter, and sighs in a way that can truly engage an audience. Our deep dive showed how with some careful prompt writing and use of tags, you can direct the AI much like a voice actor to get the desired performance. The learning curve exists, but it’s accessible – especially for creative folks used to writing scripts or directing voices. And the payoff is huge: the ability to generate versatile voice content on demand, which can save time and money, and allow for rapid iteration (change a line here, a tone there, and regenerate in seconds).
For different user groups, the value propositions are slightly different:
- Solo creators and small studios get a level playing field with bigger productions when it comes to voice work. You can have a narrator, a cast of characters, and even background ambience all with a few lines of text and no physical recording. It accelerates the creative process – no waiting for voice talent or pickups – which means more focus on storytelling and polish.
- Large studios and enterprises might use v3 as a prototyping tool or to supplement human voice work (e.g., minor characters, rapid pre-visualization of scenes). It can also open up new content avenues, like automatically generating audiobook versions of huge article archives, or personalizing customer interactions with branded AI voices that have consistent emotion.
- Listeners and end-users stand to benefit from more content (imagine more audiobooks available, including niche topics that wouldn’t have been produced otherwise) and potentially more engaging digital experiences (like apps that talk to you in a friendly, natural manner). As long as creators use the tool thoughtfully, the average consumer might soon regularly enjoy AI-voiced content that doesn’t feel robotic or cheap, but rather high-quality and enjoyable.
It’s also clear that we are in an experimental phase (it is an alpha release after all) – so there will be improvements, and sometimes you might hit a quirky output that needs tweaking. But even in this early stage, ElevenLabs v3 is demonstrating the future of human-AI interaction in media. It’s a future where creating a multilingual, emotionally resonant narration is as easy as typing your imagination into a text box.
Eleven v3 truly feels like having a versatile voice actor and sound designer living inside your computer, ready to perform whatever you write. For creative content creators, this is both exciting and empowering. The technology invites you to be imaginative – to experiment with voices and scenes that might have been out of reach before. As this AI voice frontier expands, those who embrace tools like v3 will likely find new storytelling possibilities opening up. We are witnessing the dawn of a new era in content creation, one where human creativity and artificial voices collaborate to produce something genuinely special.
