Changelog
Stay up to date with the latest features and improvements
Version 5.5.21 (Latest)
- Added support for Qwen ASR V3 and Qwen Aligner models
- Introduced automatic recording for Slack meetings
- Bulk restart for all failed tasks
- New grid layout for the job list
- Option to clear cached WAV files
- Customizable export location for transcripts and summaries
- Option to include timestamps in exported transcript and summary file names
- Recording now saved in M4A format to reduce file size
- General bug fixes, performance improvements, and UX enhancements
Version 5.0.20
- Added Mistral Online Transcription: Voxtral Mini V1 and V2
- Added ElevenLabs Online Transcription: Scribe V1 and V2
- New fine-tuned Whisper Large V3 model for Catalan
- Optimized Zoom meeting audio detection
- Bug fixes, performance improvements, and UX enhancements
Version 4.9.19
- Added AI Meeting Report viewer within TranscribeX
- Customize AI Meeting Report prompts
- Improved YouTube downloader version fetching
- Optimized Zoom meeting detection
- Moved search to the top for faster access
- AI Chat now renders full Markdown formatting correctly
- Bug fixes and performance improvements
Version 4.8.18
- Fixed microphone issues during recording
- Improved speaker diarization (0.5s segments)
- Added support for Perplexity AI
- AI Chat can respond to a specific speaker
- UI polish and bug fixes
Version 4.7.17
- Fixed an issue with YouTube downloads
- Set system microphone as default input
- Added fine-tuned Whisper Large v3 for Slovak
- AI chat messages are now persisted
- Fixed Chrome meeting detection issues
Version 4.5.15
- Auto meeting detection in Chrome for Teams and Google Meet
- AI-powered meeting summaries with action items
- Custom AI service support for summarization
- Added Sortformer speaker diarization model
- Added fine-tuned Whisper models for Arabic and Swiss German
Version 4.0.14
- Dictionary for global word replacement
- Multiple segment selection and speaker assignment
- Tags for organizing transcription jobs
- Custom OpenAI Whisper model location
- Gemini AI model additions and UI improvements
Version 3.7.13
- Voice profiles for speaker identification
- Speaker voice preview and automatic speaker colors
- Auto speaker diarization option
- Transcript paragraph formatting options
- Fullscreen video with subtitles
- General workflow and stability improvements
Version 3.5.11
- Apple Foundation Models support for local transcription
- Apple Intelligence transcript summarization
- Completed transcription notifications
- Search and replace for full transcripts
- LM Studio integration
Version 3.1.10
- Distilled Whisper Large V3 German
- Distilled Whisper Large V3 Turbo German
- Distilled Whisper Large V3 Turbo Korean
- Distilled Whisper Large V3 Chinese
Version 3.0.9
- Folder monitoring with automatic export
- Bulk export for files and folders
- Copy full AI Chat responses
- Distilled V3 and V3 Turbo support via WhisperKit
- Improved memory efficiency and freeze fixes
Version 2.5.8
- Bulk transcript export
- Support for distilled Whisper V3 and V3.5
- Bulk YouTube downloading
- Automatic transcription after import
- Ollama API integration
Version 2.0.7
- Predefined speaker profiles
- Merge duplicate speaker labels
- Auto-detect Zoom and Teams meetings for recording
- Redesigned dashboard UI
- Improved recording quality and YouTube reliability
Version 1.6.6
- Better performance for long videos
- Transcribe multiple files at once
- Drag-and-drop support
- Manual segment editing and creation tools
- Improved interface and stability
Version 1.4.5
- Added speaker diarization with Pyannote models
- macOS Tahoe 26 compatibility update
- Redesigned Home page UI
- Enhanced transcription UI usability