A native macOS app for local voice transcription powered by Whisper and Parakeet
MacTalk is a privacy-focused, menu bar app that transcribes your voice in real-time. Choose between Whisper for accuracy or Parakeet for blazing-fast, real-time streaming transcription. All processing happens locally on your Mac with Metal-accelerated inference—no cloud, no network calls, no compromises.
- Dual Engine Support - Choose Whisper for accuracy or Parakeet for ultra-fast real-time streaming
- Real-time Transcription - Streaming inference with live results as you speak
- Dual Capture Modes - Mic-only or mic + app audio (for calls/meetings)
- 100% Local Processing - Zero network calls, complete privacy
- Metal Accelerated - Optimized for Apple Silicon
- Swift 6 Concurrency - Built with Swift 6 strict concurrency for thread-safe, responsive performance
- Menu Bar App - Lightweight, always accessible
- Multiple Models - Choose from tiny (fast) to large (accurate)
- Auto-Paste - Transcripts copied to clipboard and optionally pasted
- Customizable Hotkeys - Configure your own keyboard shortcuts for hands-free control
Menu bar dropdown with recording modes, settings, and quick controls. Keyboard shortcuts for all major actions.
Live HUD overlay during transcription showing real-time waveform visualization and audio levels.
- macOS 14.0 (Sonoma) or later
- Apple Silicon (M1 or newer) recommended
- 8 GB RAM minimum
- Download
MacTalk-v1.1.0.dmgfrom Releases - Open the DMG and drag
MacTalk.appto your Applications folder - Right-click and select "Open" (first launch only)
- Grant permissions when prompted (Microphone, Screen Recording, Accessibility)
- Select a model to download (recommended: small)
See docs/development/SETUP.md for build instructions.
- Click the menu bar icon and select a transcription mode
- For call transcription, choose "Mic + App Audio" and select the app
- Press the hotkey or click "Start" to begin recording
- Speak - your words appear in real-time in the HUD overlay
- Press the hotkey or click "Stop" when done
- Transcript is automatically copied to clipboard
MacTalk supports two transcription engines:
Ultra-fast streaming transcription with real-time results. Words appear instantly as you speak.
| Model | Size | Speed | Use Case |
|---|---|---|---|
| Parakeet TDT 0.6B | ~600 MB | Instant | Real-time streaming, live dictation |
High-accuracy batch transcription with multiple model sizes:
| Model | Size | Speed | Use Case |
|---|---|---|---|
| tiny | ~32 MB | Fastest | Quick dictation |
| base | ~60 MB | Very Fast | Everyday use |
| small | ~190 MB | Fast | Recommended default |
| medium | ~539 MB | Moderate | High accuracy |
| large-v3-turbo | ~574 MB | Slower | Maximum accuracy |
Models download automatically when selected. No manual setup required.
- 100% local processing - No data ever leaves your Mac
- No telemetry - No analytics or tracking
- Open source - Review the code yourself
Microphone and Screen Recording permissions are required for transcription. Accessibility permission enables auto-paste.
A: Yes. Once models are downloaded, no network connection is required for transcription.
A: Use Parakeet for real-time streaming where words appear instantly as you speak—ideal for live dictation. Use Whisper when you need maximum accuracy or multilingual support. Start with Whisper small for balanced speed and accuracy.
A: Yes, using Mode B (Mic + App Audio). Requires Screen Recording permission.
A: Yes, Whisper supports 99+ languages. The app defaults to English for best accuracy.
A:
- MacTalk works completely offline (Apple Dictation requires network for best quality)
- Supports app audio capture for transcribing calls
- Choice of multiple models (speed vs. accuracy tradeoff)
- Privacy-focused with no telemetry or network calls
- Built with Swift 6 and AppKit for native macOS performance with strict concurrency
- Powered by whisper.cpp with Metal acceleration
- Parakeet engine via FluidAudio for real-time streaming
- Based on OpenAI Whisper and NVIDIA Parakeet
MIT License - see LICENSE for details.
- Issues: GitHub Issues
- Discussions: GitHub Discussions