Audio Generation Extension Changelog
Stay Updated with the Latest Features and Improvements
Welcome to the Audio Generation Extension Changelog page. Here, you’ll find detailed information about the latest updates, new features, and improvements made to the extension. I am committed to continuously enhancing the tool to provide you with the best audio creation experience possible. Be sure to check back regularly to stay informed about the newest enhancements and fixes.
1.0.0
Initial Release of the audio generation extension for Adobe Premiere Pro, providing basic text-to-speech functionality.
1.1.0
Added
- Integration with Elevenlabs API, enabling high-quality AI-driven audio generation with natural-sounding voices.
- Storybook feature for bulk audio generation, allowing users to create multiple audio files in a single session.
Removed
- Deprecated the manual text-to-speech input method in favor of more advanced AI-generated audio.
Fixed
- Resolved an issue causing crashes when importing large CSV files, improving stability for batch processing.
1.2.0
Added
- CSV upload functionality, enabling automated processing of multiple audio generation tasks.
- Redesigned interface for a more intuitive workflow within Adobe Premiere Pro.
- Extended compatibility to include Adobe Audition and After Effects, broadening the extension’s utility.
Removed
- Eliminated outdated interface elements to streamline the user experience.
Fixed
- Addressed a bug affecting audio playback in preview mode, ensuring accurate representation of generated audio.
- Corrected minor UI glitches in the settings menu for a smoother user experience.
1.3.0
Added
- Implemented user settings to securely save and manage the Elevenlabs API key (xi-api-key).
- Introduced an option to select specific audio tracks in Adobe Premiere Pro for direct placement of generated audio.
Fixed
- Resolved an issue preventing the saving of user settings on certain system configurations.
1.4.0
Added
- Implemented enhanced security features to better protect user data and API keys.
Updated
- Optimized performance for faster audio generation, reducing wait times for users.
- Enhanced error handling for API requests, providing more informative feedback on issues.
1.5.0
Updated
- Expanded the user manual with detailed installation instructions and comprehensive usage guidelines.
- Refined the user interface for an improved overall user experience and workflow efficiency.
1.6.0
Updated
- Enhanced documentation to provide better support for developers integrating or extending the plugin.
- Improved audio processing algorithms to deliver higher quality output across various voice types.
2.0.0
Note
Major release introducing significant improvements and new features to enhance functionality and user experience.
Added
- Implemented an improved UI for Voice Selection, including descriptive tags for easy identification.
- Integrated Elevenlabs Usage Statistics, allowing users to monitor their API usage directly within the extension.
- Introduced Speech to Speech Conversion capability, enabling users to transform existing audio with AI voices.
- Added Voice Isolation feature to separate and enhance vocal tracks in audio files.
3.0.0
Note
Another major release focusing on expanding voice options and improving user interaction.
Added
- Implemented a Voice Search function to quickly find specific voices among the growing collection.
- Integrated support for Elevenlabs Legacy Voices, preserving access to older voice models.
- Added Voice Model Selection, allowing users to choose specific AI models for each voice.
Updated
- Overhauled the User Interface, including improvements to Settings, Help sections, and slider controls.
Fixed
- Resolved issues with Batch Processing to ensure smoother handling of multiple audio generation tasks.
3.1.0
Added
- Integrated OpenAI-powered Prompt Improvement feature to enhance the quality and relevance of generated audio content.
3.2.0
Added
- Introduced options to choose MP3 Output Quality and Format, giving users more control over the final audio files.
3.3.0
Added
- Implemented customizable Adobe Premiere Pro Clip Color Labels for better organization of generated audio in projects.
3.4.0
Added
- Enhanced Output Folder Selection process for more intuitive file management.
Fixed
- Implemented a signed ZXP Installer to improve security and ease of installation.
3.5.0
Updated
- Significantly improved the User Interface for a more modern and user-friendly experience.
3.6.0
Updated
- Revamped the Help Modal with more comprehensive and accessible information.
- Redesigned the Settings Modal for easier configuration and customization.
- Implemented a robust Licensing System to manage user access and features.
Fixed
- Corrected Icon Positioning issues for a more polished appearance.
Added
- Introduced a New Manual with in-depth guidance on all features and functionalities.
3.7.0
Fixed
- Resolved character encoding issues for filenames, ensuring proper handling of special characters.
- Corrected escape sequence handling to prevent formatting errors in generated content.
3.8.0
Added
- Introduced user-friendly names for voice models to improve clarity in selection.
- Implemented specialized handling for Speech-to-Speech (STS) models, optimizing the conversion process.
- Integrated a dynamic character limit feature to adapt to different voice model capabilities.
Fixed
- Resolved inconsistencies in Voice Model selection specifically for STS functionality, ensuring proper model application.
3.9.0
Added
- Significantly improved filename generation (Now includes accurate values for stability, similarity, and style parameters.)
- Incorporates voice model information in filenames for better traceability.
Fixed
- Corrected issues with STS filenames that were showing incorrect parameter values.
4.0.0
Updated
- An improved method for selecting folders within the extension, now working smoothly in Adobe Premiere Pro.
- Added ability to search voices by both tags and names simultaneously
Removed
- Support for Adobe Audition and After Effects has been removed to focus on optimizing the experience for Premiere Pro.
4.1.0
Fixed
- Corrected the Speech to Speech icon to accurately represent the feature
- Refined ElevenLabs credit and character quota wording for improved clarity
Updated
- Redesigned the layout of the main interface for improved usability
- Added text labels under icons for easier feature identification
- Improved loading times for voice selection dropdowns
- Updated all dependencies to their latest stable versions, ensuring improved performance, security, and compatibility with modern web standards
4.2.0
Added
- Implemented Storyboard Export feature, allowing users to save storyboard entries as CSV files
- Introduced comprehensive History feature for accessing and reusing past audio generations
- Added “Insert Clip” functionality in History modal for direct timeline insertion
- Enhanced CSV import functionality to include voice model selection
Updated
- Enhanced CSV import functionality to support reimporting of exported storyboard CSV files
- Improved voice search algorithm for faster and more accurate results
- Optimized audio processing pipeline for quicker generation times
- Updated user interface for better accessibility and ease of use
Fixed
- Resolved an issue where voice model selection wasn’t properly saved in some scenarios
- Fixed a bug causing occasional misalignment of generated audio clips on the timeline
- Addressed a performance issue that could occur when handling large storyboards
4.3.0
Added
- Introduced Voice Design feature for creating custom AI voices from text descriptions
- Added support for ElevenLabs Flash Models v2 and v2.5
- Enhanced model selection with support for latest ElevenLabs voice models
- Added automatic model compatibility checking for different voice types
Updated
- Optimized interface for voice tags and labels display
- Enhanced voice model dropdown with friendly name display
- Updated voice selection interface for better user experience
- Refined model selection logic with smart fallback options
Removed
- Removed unnecessary confirmation dialog for Text to Speech generation
Fixed
- Resolved issues with voice model compatibility checking
- Addressed model selection persistence issues
- Corrected voice tag display in search results
- Fixed spinner alignment in modal windows
4.4.0
Added
- Implemented new Speed control for Text-to-Speech generation
- Added support for ElevenLabs speech rate adjustment (0.7-1.2)
- Integrated Speed parameter in Storyboard feature
- Enhanced CSV import/export with Speed parameter support
Updated
- Redesigned slider layout for better organization and usability
- Optimized voiceover controls with two-row parameter layout
- Updated help documentation with Speed parameter description
- Improved history restoration to handle Speed parameter values
Changed
- Reorganized TTS parameter controls for better space utilization
Fixed
- Addressed parameter persistence when switching between audio types
- Fixed slider value display consistency across different contexts
4.5.0
Added
- Restructured Settings JSON with Fallback Location
4.6.0
Fixed
- Fallback with Polyfill
- Improved JSON-Object for color label settings and better error handling
5.0.0
Note
Major architectural overhaul introducing comprehensive code modularization, enhanced user interface, and significant performance improvements. This release represents a complete modernization of the extension with focus on scalability, maintainability, and user experience.
Added
- Modular Architecture: Complete code restructuring into organized modules:
- Core modules (API, Config, Event Manager, License, Tab Manager)
- Feature modules (Voiceover, Sound Effects, Speech-to-Speech, Audio Isolation, Storyboard, Voice Design, History)
- UI modules (Modals, Voice Selector, Form Controls, Tooltips, Tab Icons, Drag-Drop, Voice Tooltips)
- Integration modules (Premiere, File Management, CSV, MCP)
- Utility modules (Helpers, Storage, Audio, Debug Console, Template Loader)
- Revolutionary Rotary Controls: Introduced premium rotary knob interface for audio parameter adjustments using jQuery rotarySwitch plugin
- High-quality knob graphics with retina display support
- Intuitive click-to-edit value functionality
- Smooth rotation animations and visual feedback
- Responsive scaling for narrow panel environments
- Advanced Track Selection Grid: Implemented visual grid-based audio track selection system
- Interactive grid buttons replacing traditional dropdown menus
- Real-time visual feedback and selection states
- Responsive layout adapting to panel width
- Enhanced accessibility and faster workflow integration
- MCP (Model Context Protocol) Integration: Full server integration for enhanced AI capabilities
- Dedicated MCP server directory configuration
- Advanced prompt processing and context management
- Enhanced AI-powered content generation workflows
- Enhanced Drag & Drop Interface: Comprehensive file upload system with visual feedback
- Multi-state visual indicators (idle, hover, dragover, has-file, error)
- Animated feedback for file operations
- Error handling with shake animations
- Support for audio file preview and management
- Advanced Voice Model Grid Selection: Visual model selection interface
- Grid-based layout for voice model selection
- Compatibility checking for different voice types
- Smart fallback options and error handling
- Support for latest ElevenLabs model variations
- Comprehensive Voice Favorites System: Complete favorite voice management
- One-click favorite/unfavorite functionality
- Dedicated favorites section in voice dropdown
- Visual golden star indicators for favorited voices
- Persistent favorite status across sessions
- Recent Voices Tracking: Automatic recent voice history
- Dynamic recent voices section in dropdowns
- Intelligent usage-based ordering
- Seamless integration with existing voice selection
- Integrated Voice Search: Advanced search functionality within dropdowns
- Real-time search as you type
- Search by voice name and tags simultaneously
- Sticky search bar with smooth scrolling
- No results messaging and clear search states
- Enhanced Voice Tooltips: Detailed hover information system
- Rich voice information on hover
- Voice descriptions, tags, and metadata display
- Smooth fade-in/out animations
- Responsive positioning and sizing
- Advanced History Pagination: Comprehensive history browsing
- Multi-page history navigation with page controls
- Configurable results per page (10-1000 items)
- Voice filtering and audio track selection
- Direct timeline insertion from history
- Responsive Design System: Complete responsive layout overhaul
- Adaptive layouts for narrow Adobe panels (down to 200px width)
- Intelligent element scaling and repositioning
- Optimized spacing and typography for small screens
- Touch-friendly interface elements
- Enhanced Modal System: Improved modal windows with better UX
- Smooth transition animations
- Better content organization and spacing
- Improved accessibility and keyboard navigation
- Responsive modal sizing
Updated
- Complete UI/UX Redesign: Comprehensive visual and interaction improvements
- Modern color scheme with CSS custom properties
- Enhanced button styling with gradient effects and shadows
- Improved form control spacing and alignment
- Consistent typography and sizing throughout
- Advanced Voice Selection Interface: Revolutionary dropdown experience
- Multi-section organization (Favorites, Recent, All Voices)
- Enhanced voice option layout with tags and descriptions
- Improved play button integration and audio preview
- Better visual hierarchy and information density
- Optimized Audio Parameter Controls: Premium control interface
- Rotary knobs for professional audio parameter adjustment
- Visual value display with click-to-edit functionality
- Smooth parameter transitions and visual feedback
- Industry-standard control layout and behavior
- Enhanced Character Counting: Advanced text limit management
- Dynamic character counting with visual warnings
- Color-coded feedback (normal, warning, error states)
- Model-specific character limit adaptation
- Real-time updates across all text fields
- Improved Icon System: Comprehensive icon and visual updates
- Higher resolution icons for retina displays
- Consistent icon sizing and alignment
- Enhanced visual feedback and hover states
- Professional iconography throughout interface
- Optimized Performance: Significant speed and efficiency improvements
- Modular loading for faster initialization
- Optimized event handling and memory management
- Reduced bundle size through code splitting
- Enhanced caching and storage mechanisms
- Enhanced Accessibility: Improved screen reader and keyboard support
- Better ARIA labels and semantic markup
- Improved focus management and visual indicators
- Enhanced keyboard navigation throughout interface
- Screen reader friendly content structure
Changed
- Code Architecture: Complete modular restructuring for better maintainability
- Separation of concerns across functional modules
- Improved code organization and documentation
- Enhanced error handling and debugging capabilities
- Better dependency management and loading
- Interface Layout: Optimized spacing and component arrangement
- Reduced unnecessary whitespace and improved density
- Better visual grouping of related controls
- Enhanced information hierarchy and flow
- Streamlined workflow for common tasks
- Control Interactions: Enhanced user interaction patterns
- More intuitive drag and drop behaviors
- Improved feedback for all user actions
- Smoother animations and transitions
- Better error messaging and recovery
Fixed
- Voice Model Compatibility: Resolved voice model selection persistence issues
- Fixed model selection not saving properly in certain scenarios
- Corrected model compatibility checking for different voice types
- Addressed Smart fallback option failures
- Audio Timeline Alignment: Fixed occasional audio clip misalignment issues
- Resolved timeline insertion positioning problems
- Fixed audio track selection persistence
- Corrected clip color label application
- Performance Optimization: Addressed performance issues with large datasets
- Fixed memory leaks in voice loading and selection
- Improved handling of large voice collections
- Optimized dropdown rendering for better responsiveness
- Responsive Layout Issues: Corrected various layout problems on narrow panels
- Fixed element overflow and wrapping issues
- Resolved scaling problems with rotary controls
- Corrected modal positioning on small screens
- Voice Search Functionality: Fixed search accuracy and performance
- Resolved case sensitivity issues in voice search
- Fixed tag-based search not working properly
- Improved search result relevance and ordering
Removed
- Legacy Slider Controls: Replaced traditional sliders with rotary knobs
- Removed old horizontal slider interface
- Eliminated outdated parameter adjustment methods
- Outdated Interface Elements: Streamlined interface by removing deprecated components
- Removed unnecessary confirmation dialogs
- Eliminated redundant UI elements
- Simplified overcomplicated workflows
5.1.0
Added
- Eleven v3 Model Support: Full integration of ElevenLabs’ Eleven v3 voice model
- Three specialized modes: Creative (0.0), Natural (0.5), and Robust (1.0)
- Optimized UI controls for v3 model with discrete stability settings
- Automatic hiding of unused parameters (Similarity, Style, Speed) in v3 mode
- Character limit adjusted to 3000 characters for v3 model (both Voiceover and Storyboard)
- Audio Tag Library for Eleven v3: Comprehensive audio tag system with 1400+ tags
- Right-click context menu in prompt field when v3 model is selected
- Organized categories: Mood, Environment, Tone, Style, Emotion, and more
- Tags loaded from CSV library for easy customization and updates
- Smart tag insertion with automatic spacing
- Break/Pause Tag System: Insert timed pauses in voiceovers (all models)
- New pause button next to AI Inspiration button
- Quick preset buttons: 0.5s, 1.0s, 1.5s, 2.0s, 3.0s
- Custom slider for precise duration control (0.1s – 5.0s)
- Automatic <break time=”X.Xs” /> tag insertion at cursor position
- Works with all voice models, not just Eleven v3
- AI-Powered Text Enhancement for Eleven v3:
- Enhanced “Inspiration” feature with v3-specific audio tag integration
- OpenAI GPT automatically analyzes text and inserts appropriate audio tags
- Separate enhancement prompts for v3 and standard models
- Improved expressiveness and emotional delivery through intelligent tag placement
- OpenAI Model Selection: Configure which OpenAI model to use for text enhancement
- Support for GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, and other models
- Model selection available in Settings panel
- Flexible configuration for different use cases and API tiers
- Extended SFX Duration: Sound effect generation now supports up to 30 seconds
- Increased from previous 22-second limit
- Better support for longer ambient sounds and extended effects
- Rotary control updated to reflect new maximum duration
- Loop Support: Enable seamless looping for generated audio
- New loop option for sound effects
- Perfect for background ambience and continuous soundscapes
Updated
- ElevenLabs API Integration: Updated to latest API endpoints
- Improved error handling and response parsing
- Enhanced compatibility with new ElevenLabs features
- Updated voice model fetching for better reliability
- Help Documentation: Comprehensive updates for new features
- Detailed Eleven v3 section with model modes and audio tags
- Break/Pause tag usage guide with best practices
- Step-by-step instructions for all new features
- Enhanced troubleshooting section
- Character Counter Logic: Dynamic character limits based on voice model
- Voiceover: 3000 chars for v3, 5000 chars for other models
- Storyboard: Model-aware character limits per entry
- Real-time updates when switching between models
- Visual indicators (color-coded) for approaching limits
Changed
- Voice Model UI: Improved model selection interface
- Grid-based model selection for better visual clarity
- Enhanced v3 model indicators and labels
- Automatic UI adaptation based on selected model
- Streamlined controls for model-specific parameters
- Prompt Input Layout: Redesigned prompt area with integrated tools
- AI Inspiration and Pause buttons side-by-side (gap: 0px)
- Cleaner, more compact layout
- Better visual hierarchy for prompt enhancement tools
Fixed
- Voice Model Persistence: Resolved model selection issues in Storyboard
- Fixed model not updating correctly when switching between entries
- Improved synchronization between visible and hidden model selects
- Enhanced character count updates when model changes
- Context Menu Positioning: Improved menu placement logic
- Better edge detection to prevent off-screen menus
- Smart positioning for both Audio Tags and Pause menus
- Responsive to window resize and scroll events