OpenSuperWhisper is a macOS application that provides real-time audio transcription using the Whisper model. It offers a seamless way to record and transcribe audio with customizable settings and keyboard shortcuts.
- 🎙️ Real-time audio recording and transcription
- 🧠 Two transcription engines: Whisper and Parakeet — download models directly from the app
- ⌨️ Global keyboard shortcuts — key combination or single modifier key (e.g. Left ⌘, Right ⌥, Fn)
- ✊ Hold-to-record mode — hold the shortcut to record, release to stop
- 📁 Drag & drop audio files for transcription with queue processing
- 🎤 Microphone selection — switch between built-in, external, Bluetooth and iPhone (Apple Continuity) mics from the menu bar
- 🌍 Support for multiple languages with auto-detection
- 🇯🇵🇨🇳🇰🇷 Asian language autocorrect (autocorrect)
brew update # Optional
brew install opensuperwhisperOr from GitHub releases page.
- macOS (Apple Silicon/ARM64)
If you encounter any issues or have questions, please:
- Check the existing issues in the repository
- Create a new issue with detailed information about your problem
- Include system information and logs when reporting bugs
To build locally, you'll need:
git clone git@github.com:Starmel/OpenSuperWhisper.git
cd OpenSuperWhisper
git submodule update --init --recursive
brew install cmake libomp rust ruby
gem install xcpretty
./run.sh build
In case of problems, consult .github/workflows/build.yml which is our CI workflow
where the app gets built automatically on GitHub's CI.
Contributions are welcome! Please feel free to submit pull requests or create issues for bugs and feature requests.
- Streaming transcription
- Custom dictionary / keyword boosting (#19)
- Intel macOS compatibility (#15)
- Agent mode (#14)
- Background app (#8)
- Support long-press single key audio recording (#18)
OpenSuperWhisper is licensed under the MIT License. See the LICENSE file for details.
You can download Whisper model files (.bin) from the Whisper.cpp Hugging Face repository. Place the downloaded .bin files in the app's models directory. On first launch, the app will attempt to copy a default model automatically, but you can add more models manually.