Fully open source voice-to-text dictation app for macOS with AI enhancement.
Get the latest release from here
Important
This project is completely free and open source. If you find FluidVoice useful, please star the repository. It helps with visibility and motivates continued development. Your support means a lot.
FluidVoice_1.5_cmd_mode.mp4
writemode_FluidVoice_1.5.mp4
- Overlay with Notch support
- Command Mode
- Write Mode
- New History stats
- Stats to monitor usage
- Live Preview Mode: Real-time transcription preview in overlay
- Real-time transcription using Parakeet TDT v3 model
- AI enhancement with OpenAI, Groq, and custom providers
- 25+ languages with auto-detection
- Global hotkey for instant voice capture
- Smart typing directly into any app
- Menu bar integration for quick access
- Auto-updates with seamless restart
- Download the latest release
- Move to Applications folder
- Grant microphone and accessibility permissions when prompted
- Set your preferred hotkey in settings
- Optionally add an AI provider API key for enhanced transcription
- macOS 14.0 (Sonoma) or later
- Apple Silicon Mac (M1, M2, M3, M4)
- Intel Macs are not currently supported. If you need Intel support, please create an issue to help gauge demand.
- Microphone access
- Accessibility permissions for typing
git clone https://github.com/altic-dev/Fluid-oss.git cd Fluid-oss open FluidVoice.xcodeprojBuild and run in Xcode. All dependencies are managed via Swift Package Manager.
Contributions are welcome! Please create an issue first to discuss any major changes or feature requests before submitting a pull request.
Follow development updates on X: @ALTIC_DEV
This project is licensed under the Apache License 2.0.