Changelog
Stay up to date with the latest features and improvements
1.6.5
Improvements
- Cohere is now the default local model on non ARM machines
- Download progress UI for model dependencies in the Models library
- Press Enter to save when editing a speaker names
- Reprocessing a recording with a different mode no longer changes your active mode
1.6.2
Features
- Windows context menu integration "Open with..." and Show more options "Transcribe with Superwhisper"
- Extended support for `.opus` files
- Whisper models are now free
- Free Pro trial now counted in words instead of minutes
- S1-mini is now generally available
- Tone control for Message, Mail, and Notes modes
- In-app updates for local models
- Faster launch and time to transcription-ready
- Whisper models renamed to Tiny, Base, Small, Medium, and Large
1.5.10
Features
- All-time stats view with X share card
- Updated S1-Mini model with tone control
- Cohere Transcribe is now marked as stable
- Word-by-word playback highlighting in History
- S1 announcement modal
- Significant performance boost for local Whisper models
- Vocabulary support for local Whisper models
- Updated application icon
- Smoother multipart model download progress updates
- Elevenlabs Scribe real-time "no voice found" fix
- Super mode parsing fix to remove errant `
` tags in responses
1.5.8
Features
- Added Cohere Transcribe model with Vocabulary support via our new Supervocab engine
- Added sound effect theme selection
- Added proxy support (WPAD and PAC)
- Added `record/start` and `record/stop` deep links for controlling recording from external tools
- Model selector now has arrow-key navigation
- Models that your system can't run are no longer available to download
- Updated the history info drawer UI
- Updated the reprocess button and its popout
- Experimental feature icons now sit beside their toggles and light up when active
- Added hover states to the vocabulary input buttons
- Improved model dependency system
- Fixed Settings window drag in history item full-view
- Fixed "popular" model options
- Fixed history transcript copying (full, segmented, and speaker-formatted output)
- Fixed sound effects toggle not being respected at launch
- Fixed the help message icon position
- Fixed escape key navigation when in history item full-view with info drawer open
- Fixed history info drawer timestamp format
- Fix cohere auto language detection
1.5.1
New Features
- Run language models fully on-device with the new experimental Superwhisper S1-mini model — no cloud required
- New (experimental) Parakeet multi language real-time model for live transcription across more languages
- Automatic fallback to raw transcription if a language model fails, so you never lose a recording
- New "Supervocab" vocabulary engine for local whisper models
- Faster microphone initialization between recordings
- Mode keyboard shortcut moved out of Advanced settings for easier access
- Improved model library table layout
- Smooth transitions between "AI Processed", "Original" and "Segmented" history item views
- Language picker search input
1.4.13
New Features
- Use Opus audio format with compatible voice models for substantially faster cloud transcriptions
- Per-mode auto-capitalize insert / smart capitalization toggle
- Support for streaming language model responses
- Region routing for cloud transcriptions — requests are now routed to the lowest-latency region for faster turnaround
- Implement smooth scrolling for long transcription results in recording window
- History list performance enhancements
- Make vocabulary input inner buttons clickable
- Superwhisper S1 transcriptions now display word-level segments correctly in the history view
- Migrate user config files from Roaming to Local in prep for Filesync feature implementation
- User can now use enter key to close/accept error windows
- Fix per-mode shortcut triggering
- Fix per-mode shortcut active mode revert issue
1.4.0
Features and Fixes
- Support for Parakeet local models on ARM based processors
- Models Library view for browsing, downloading and creating your own custom models
1.3.13
Features and Fixes
- Mode specific keyboard shortcuts
- All model files downloaded from Superwhisper host
- Implement license email change requests
- Move dynamic normalization to sound settings
- Mode change keyboard shortcut helper at bottom of modes list
- Advanced settings UI rework
- Add Opus 4.6 and 4.7 to custom model setup
- History search and multi select UI rework
- Fix bug with disabled but still clickable speaker separation toggle
1.3.12
Features and Fixes
- Vocabulary UI redesign
- Fix modes UI load time issues
- Add support for Azure Foundry custom model endpoints
- Crash fixes
1.3.11
Features and Fixes
- Modes UI overhaul
- Activation Apps UI and indexing overhaul
- Clickable timestamps in History segment view
- Model favorites UI
- Multiple crash fixes
- Fix custom Anthropic model creation flow
- Fix crash on drag recording window between monitors
1.3.9
Features and Fixes
- Toggle for "Automatically increase microphone volume" for improved voice detection
- Toggle for "Silence removal" to improve accuracy and reduce hallucinations
- Add mouse button shortcut for recording toggle and push-to-talk
- Add clipboard behavior preference to allow clipboard bypass and restoration
- "Identify Speakers" feature for Whisper, Parakeet Multi-language and most cloud models, including speaker naming UI
- SV-1 and SL-1 are now model defaults
- Context-menu on Settings -> Modes items right-click with duplicate, delete and set active
- History full-window view for long transcriptions
- Progress indicator for file decoding and transcription progress (applies to Whisper and Parakeet models)
- Elevenlabs Scribe V2 model with real-time support (currently available as an experimental model)
- Complete overhaul of onboarding flow with microphone check and default model selection
- License UI overhaul with improved deeplink handling
1.3.6
Features and Fixes
- Improved space insertion logic
- Add VAD state reset, should resolve repeated "no voice found" errors
- Add error notification for proper noun extractor initialization
- Add error notification for tray icon initialization
- Add quit option to recording window context menu
1.3.5
Features and Fixes
- Add "Always close recording window" toggle for hiding transcription result regardless of paste success
- Add user notifications for audio stream errors
1.3.4
Features
- Parakeet English only model with real-time support added
- Global playback behavior config — set a default that can still be overridden per mode
- Brighter UI throughout the app
- Re-styled keyboard shortcut inputs for a cleaner look
- Removed push-to-talk toggle — clear the shortcut to disable push-to-talk instead
- Sound effects volume control added to settings
- Enhanced audio engine is now the default
- Recording window right-click context menu with Settings and Resize options
- Discard recording confirmation when cancelling recordings longer than 30 seconds
- Alert with shortcut to control panel shown when no audio inputs are available
- Improved activation app indexing performance
- Improved recording error notifications
- Faster initialization
- Faster session cancellation
- Fixed recording window freeze on drag bug
- Fixed unclickable expand icon when "Start Recording" is shown
- Fixed stuck key scenarios
- Fixed audio input stream setup with a fallback mechanism
- Fixed recording window system close bug
- Fixed unable to delete pro models after trial expiry
- Added crash handlers for inaccessible config files
- Improved file resampling performance
- HOTFIX: v1.3.3 -> 1.3.4 Onboarding not displaying shortcuts
1.2.32
Features and Fixes
- Add GPT-5.3 Instant
- Add Realtime transcription Deepgram voice models
- Note: Must have advanced audio engine enabled. Realtime toggle found in advanced mode configuration drawer.
- Fix Push-to-talk / Toggle shortcut conflict issues
- Fix Realtime toggling bug
1.2.30
Features and Fixes
- Add GPT-5.3 Instant
- Add Realtime transcription Deepgram voice models
- Note: Must have advanced audio engine enabled. Realtime toggle found in advanced mode configuration drawer.
- Fix Push-to-talk / Toggle shortcut conflict issues
1.2.7
Fixes
- Fix Parakeet model download checksum error
1.2.6
Features and Fixes
- History multi-select + delete
- History info drawer UI overhaul
- Fix history search results sticking after Settings tab switch
- Add keyboard shortcut support for IntlYen, IntlRo, Convert + Fix KeyF binding conflict
1.2.5
Features and Fixes
- New Gemini and Grok language models
- New OpenAI and Anthropic models
- Enable/disable toggle for activation app indexing
- General release (no longer experimental) for Parakeet
- Fix: Check internet connection when using Parakeet
- Fix: Hide organization model delete button
1.1.9
Features and Fixes
- Added per-mode auto paste toggle
- Add microphone select to tray menu (only available with Enhanced Audio enabled)
- Handle paste error when pasting into apps with elevated privileges
- Predefined mode prompt improvements
- Fix replacement case sensitivity issues
- Whisper model stability improvements
1.1.6
Features and Fixes
- Address keyboard shortcut binding issues
- Add recording issue report upload flow
1.1.4
Features and Fixes
- Keyboard & Controls: Overhauled keyboard interactions with single-key shortcuts, extended shortcut options
- Enhanced Audio Engine: Improved stability and sample format compatibility and faster initialization,
- Fixed record from system audio timing, and added experimental dynamic normalization (Settings → Sound) toggle
- API & Models: Fixed Groq BYOK and custom model endpoint issues
1.1.0
Features and Fixes
- Add GPT 5.1 language model
- Recording retention period / auto-deletion period
- Collapsible Settings window sidebar
- History UI updates including segment view
- Recording window style selector
1.0.10
Features and Fixes
- Fix transcription vocab and replacements I/O error
- Fix activation app indexing crash
- Dependency updates, including some model runtime performance improvements
1.0.9
Features and Fixes
- Redesigned recording window and mini mode selector
- Fix missing whisper model file errors when using Ultra
- Fix parakeet timeout issue
- Fix error when cancelling transcribe from file
- Model picker design update
1.0.8
Features and Fixes
- NEW Parakeet Multi-language model (Experimental feature)
- Fix model hallucination removal of 'Thank you' and other common phrases
- Improved empty transcription handling
- Fix whisper inference timeout issue for longer recordings
1.0.5
Features and Fixes
- Ollama provider for custom models
- Fix Whisper model transcription cancellation
- Fix vocabulary deletion button not visible for some users
- Fix crash on indexing activation apps
- Dark mode UI improvements
1.0.4
Features and Fixes
- Fix SL1 LLM response missing after some transcriptions
- Fix pre-initialization deeplink activation bug
- Fix recording window handle error
- Fix error toggling window effects on some versions of windows
1.0.3
Features and Fixes
- Stats view with typing speed and time saved
- Improved history indexing and keyword search
- Add Turkish language support
1.0.2
Features and Fixes
- Enhanced audio engine (experimental feature).
- Improved handling of long recordings
- Improved processing of large audio files
- Ability to record from system audio (found in mode configuration)
- Enterprise organization models and feature gating
1.0.0
Features and Fixes
- Onboarding updates
- Update discord server links
- Allow override of mode set by activation apps