Voice to Copilot
Transform your voice into GitHub Copilot Chat commands instantly with the power of OpenAI Whisper, right inside Visual Studio Code! Perfect for hands-free coding and AI assistance.
🎤 Features
- High-Quality Transcription: Leverages OpenAI's Whisper API for accurate speech recognition
- Multiple Insert Modes: Send transcriptions to GitHub Copilot Chat, active editor, or clipboard
- Real-time Recording: Live audio recording with visual status indicators
- Multi-language Support: Configure your preferred language for transcription
- Flexible Audio Input: Works with any DirectShow-compatible audio device
- Keyboard Shortcuts: Quick access with customizable hotkeys
🚀 Quick Start
- Install the Extension: Search for "Voice to Copilot" in VS Code marketplace
- Configure OpenAI API: Add your OpenAI API key in settings
- Set up FFmpeg: Configure path to FFmpeg executable
- Start Recording: Click the microphone icon in status bar or use
Ctrl+Alt+R
⚙️ Configuration
Required Settings
Open VS Code settings (Ctrl+,
) and configure:
Setting |
Description |
Example |
simpleSpeech.openaiApiKey |
Your OpenAI API key |
sk-... |
simpleSpeech.ffmpegPath |
Path to FFmpeg executable |
C:\ffmpeg\bin\ffmpeg.exe |
Optional Settings
Setting |
Default |
Description |
simpleSpeech.audioDevice |
Line (MG-XU) |
Audio input device name |
simpleSpeech.language |
de |
Transcription language (ISO 639-1) |
simpleSpeech.insertTarget |
copilot-chat |
Where to insert text |
Insert Target Options
- copilot-chat: Send transcription directly to GitHub Copilot Chat
- editor: Insert at cursor position in active editor
- clipboard: Copy transcription to clipboard
🛠️ Prerequisites
1. OpenAI API Key
- Create an account at OpenAI
- Generate an API key with access to Whisper API
- Add the key to extension settings
2. FFmpeg Installation
Download FFmpeg from ffmpeg.org and:
Windows:
# Download from https://www.gyan.dev/ffmpeg/builds/
# Extract to C:\ffmpeg
# Add C:\ffmpeg\bin to PATH or configure absolute path in settings
macOS:
brew install ffmpeg
# Or configure path: /opt/homebrew/bin/ffmpeg
Linux:
sudo apt install ffmpeg
# Or: sudo yum install ffmpeg
🎯 Usage
Status Bar Control
- 🎤 Aufnahme: Click to start recording
- 🔴 Recording...: Click to stop recording
- ⏳ Transkribierung...: Processing in progress
Command Palette
Simple Speech: Start Speech Recording
Simple Speech: Stop Speech Recording
Simple Speech: Toggle Speech Recording
Keyboard Shortcuts
Ctrl+Alt+R
: Toggle recording (customizable)
🎨 Workflow Examples
1. Code Documentation
1. Start recording while reviewing code
2. Speak: "This function validates user input and returns sanitized data"
3. Transcription appears in GitHub Copilot Chat
4. Refine with Copilot for perfect documentation
2. Quick Notes
1. Set insert target to "editor"
2. Open a markdown file
3. Record your thoughts and ideas
4. Text appears directly at cursor position
3. Accessibility
1. Set insert target to "clipboard"
2. Record speech for any application
3. Paste transcribed text anywhere
🌍 Language Support
Supported languages include:
en
- English
de
- German
fr
- French
es
- Spanish
it
- Italian
pt
- Portuguese
ru
- Russian
ja
- Japanese
ko
- Korean
zh
- Chinese
- And many more...
See OpenAI Whisper documentation for complete language list.
🔧 Troubleshooting
Audio Device Issues
- Check Windows Sound settings for correct device name
- Use exact device name in
simpleSpeech.audioDevice
setting
- Test with Command Prompt:
ffmpeg -list_devices true -f dshow -i dummy
FFmpeg Not Found
- Verify FFmpeg installation:
ffmpeg -version
- Use absolute path in settings if not in PATH
- Ensure FFmpeg supports DirectShow on Windows
API Errors
- Verify OpenAI API key validity
- Check API usage limits and billing
- Ensure Whisper API access is enabled
No Transcription Output
- Check audio device is working and not muted
- Speak for at least 2-3 seconds
- Verify internet connection for API calls
📝 Privacy & Security
- Audio Processing: Audio is sent to OpenAI's Whisper API for transcription
- API Key: Stored locally in VS Code settings, never shared
- No Data Storage: Extension doesn't store recordings or transcriptions
- Temporary Files: Audio buffers are processed in memory only
🤝 Contributing
Found a bug or have a feature request?
- Issues: GitHub Issues
- Pull Requests: Contributions welcome!
- Feedback: Leave a review on VS Code Marketplace
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- OpenAI Whisper: For excellent speech recognition capabilities
- FFmpeg: For reliable audio processing
- VS Code Team: For the extensible editor platform
Enjoy hands-free coding! 🎤→📝