f94265e4c5
- Add Quick Install section for DMG download - Add Build from Source section for developers - Add Whisper model comparison table (tiny/base/small/medium) - Note about Intel Mac performance - Note about Accessibility permission after updates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
3.4 KiB
3.4 KiB
WhisperDictate
A simple menu bar app for voice dictation using OpenAI Whisper (local, offline).
Platforms
| Platform | Language | Status |
|---|---|---|
| macOS | Swift | ✅ Ready |
| Linux | Rust | 🔜 Planned |
| Windows | C# | 🔜 Planned |
macOS
Features
- 🎤 Global hotkey (⌃⌥D) to start/stop recording
- 🔒 Fully offline - uses local Whisper model
- ⚡ Automatic paste into any focused app
- ⚙️ Settings window (language, model path, sounds)
- 🚀 Launch at login support
Requirements
- macOS 13.0+
- Apple Silicon (M1/M2/M3) or Intel Mac
- whisper-cpp (
brew install whisper-cpp) - Whisper model file
Quick Install (Download)
- Download the latest DMG from Releases
- Open the DMG and drag WhisperDictate to Applications
- Install dependencies:
# Install whisper-cpp
brew install whisper-cpp
# Download Whisper model
mkdir -p ~/.whisper-models
curl -L -o ~/.whisper-models/ggml-medium.bin \
"https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.bin"
- Launch WhisperDictate and grant permissions (Microphone + Accessibility)
Build from Source
If you prefer to build the app yourself:
# Clone the repository
git clone https://github.com/hariel1985/WhisperDictate.git
cd WhisperDictate/macos
# Build and install to /Applications
make install
# Or just build without installing
make build
Build Commands
| Command | Description |
|---|---|
make build |
Compile the app |
make install |
Build and install to /Applications |
make run |
Build and run |
make dmg |
Create distributable DMG |
make clean |
Remove build artifacts |
Usage
- Launch WhisperDictate from Applications
- Look for the 🎤 icon in your menu bar
- Press ⌃⌥D (Control + Option + D) to start recording
- Speak (icon changes to 🔴)
- Press ⌃⌥D again to stop and transcribe
- Text is automatically pasted where your cursor is
Settings
Click the menu bar icon → Settings to configure:
- Language: 31 supported languages (dropdown)
- Model Path: Path to your Whisper model file
- Sound feedback: Toggle audio feedback on/off
- Launch at login: Start automatically when you log in
Whisper Models
| Model | Size | Speed | Accuracy | Download |
|---|---|---|---|---|
| tiny | 75 MB | Fastest | Basic | Download |
| base | 142 MB | Fast | Good | Download |
| small | 466 MB | Medium | Better | Download |
| medium | 1.5 GB | Slow | Best | Download |
For Intel Macs, consider using small or base models for faster transcription.
Audio Feedback
- 🔔 Tink - Recording started
- 🔔 Pop - Recording stopped, processing
- 🔔 Glass - Success, text pasted
- 🔔 Basso - Error
Permissions
Grant these in System Settings → Privacy & Security:
- Microphone - for recording
- Accessibility - for auto-paste
Note
: After reinstalling or updating, you may need to remove and re-add the app in Accessibility settings.
License
MIT License