Changelog

Stay up to date with the latest features and improvements.

Version 9.0.32 (Latest)

Created: 2026-08-05

Added command-line interface (CLI) support
Added Model Context Protocol (MCP) support
Added support for the ElevenLabs Scribe v2 Realtime model
Fixed an issue that could cause static noise in recordings
Fixed a crash that could occur when transcription reached 100%
General bug fixes, performance improvements, and UX enhancements

Version 8.8.31

Created: 2026-07-23

Automatically start transcribing after meeting recordings end
Automatically select the default microphone for meeting recordings
Added the option to download the LLM model during onboarding
Added a 2-second delay before starting meeting recordings
General bug fixes, performance improvements, and UX enhancements

Version 8.7.30

Created: 2026-07-15

Added a new fine-tuned Whisper Large model for Hinglish
Added the ability to edit an existing bulk task
Fixed an issue where Slack video recording captured the incorrect window
Fixed the calendar event matching issue
Fixed the speaker issue in bulk exports
General bug fixes, performance improvements, and UX enhancements.

Version 8.6.29

Created: 2026-07-05

Polished Teams meeting auto-detection
Fixed an issue where video recording captured the incorrect window
Added the ability to customize the AI timeout interval
Added the ability to cancel an ongoing AI request
Added the option to select which calendar provides the meeting name
Fixed a bulk transcription export issue affecting MKV files
General bug fixes, performance improvements, and UX enhancements.

Version 8.5.28

Created: 2026-07-01

Added meeting auto-detection support for custom apps (e.g., Phone, Brave).
Added the ability to record apps as video instead of just audio.
Use the Mac Calendar event name as the recording name.
In bulk export, added the ability to toggle timestamps.
Adjusted the timestamp format in the exported CSV file.
General bug fixes, performance improvements, and UX enhancements.

Version 8.1.27

Created: 2026-06-19

Fix the crash when new meeting detected
General bug fixes, performance improvements, and UX enhancements

Version 8.0.26

Created: 2026-06-13

New Dictation
Added AI-powered text polishing for dictation
Added an option to display translations only in Live View
Redesigned the caption overlay for live transcriptions
Integrated permission requirements into the onboarding process
Added meeting auto-detection for Safari, Discord, and Webex
Added support for exporting AI summaries and transcripts into a single Markdown file
Included user notes within AI-generated summaries
Upgraded the Youtube downloader
General bug fixes, performance improvements, and UX enhancements

Version 7.6.25

Created: 2026-06-01

Improved OpenAI Whisper transcription speed and accuracy
Added additional fine-tuned Whisper models
Enhanced Zoom meeting detection
Added new variables for meeting summary prompts
Included speaker names in AI-generated summaries
General bug fixes, performance improvements, and UX enhancements

Version 7.0.23

Created: 2026-05-19

Significant improvements to Speaker Diarization accuracy
Added Parakeet streaming models (160ms / 320ms / 1280ms) for Live Caption
Live transcription can now continue running even when the app window is closed
Added real-time translation support for Live Caption
Added in-meeting AI Chat support for Live Caption
Added customizable font size and font styles for Live Caption
Added translucent view mode for Live Caption
Added support for local LLM models, including Qwen and Gemma
Added fine-tuned Whisper Large V3 French model
Improved Whisper transcription speed and accuracy
Added more pre-defined prompts for live meetings
Removed Sortformer since Pyannote diarization is now highly accurate
General bug fixes, performance improvements, and UX enhancements

Version 6.0.22

Created: 2026-04-30

Real-time transcription for recordings
Real-time transcription for meetings
Automatically save recordings when you choose not to transcribe after recording
Translate using the AI Service
General bug fixes, performance improvements, and UX enhancements

Version 5.5.21

Created: 2026-03-26

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

Created: 2026-03-07

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

Created: 2026-02-19

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

Created: 2026-02-10

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

Created: 2026-02-04

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

Created: 2026-01-22

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

Created: 2026-01-11

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

Created: 2025-12-28

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

Created: 2025-12-11

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

Created: 2025-12-03

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

Created: 2025-11-28

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

Created: 2025-11-17

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

Created: 2025-11-07

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

Created: 2025-10-25

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

Created: 2025-10-09

Added speaker diarization with Pyannote models
macOS Tahoe 26 compatibility update
Redesigned Home page UI
Enhanced transcription UI usability