silent-speech 0.1.1

Real-time audio visualization and voice-to-text chat interface with Gemini AI

Silent Speech 🎙️

Real-time audio visualization and voice-to-text chat interface powered by Google's Gemini AI.

Features ✨

• 🎯 Real-time Audio Capture - Live microphone input with visual waveform
• 🤖 Gemini AI Integration - Accurate speech-to-text transcription
• 📋 Auto Copy to Clipboard - Toggleable automatic clipboard copying
• 🎨 Rich Terminal UI - Beautiful, responsive interface with color coding
• ⌨️ Keyboard Controls - Intuitive hotkeys for all functions
• 🔇 Noise Filtering - Intelligent filtering of breathing sounds and filler words
• 🚀 Non-blocking Processing - Responsive UI during transcription

Installation 📦

Via pip (Recommended)

pip install silent-speech

From Source

git clone https://github.com/laspencer91/silent-speech.git
cd silent-speech
pip install -r requirements.txt
python -m silent_speech.main

Quick Start 🚀

1. Set up Gemini API Key:

   export GEMINI_API_KEY="your-api-key-here"
   

2. Run the application:

   silent-speech
   

3. Start using:

   • Press SPACE to start recording
   • Press SPACE again to stop and transcribe
   • Press Q to quit
   • Press A to toggle auto-copy
   • Press C to copy the last response

System Requirements 🖥️

• Python 3.8+
• Microphone access
• Internet connection (for Gemini API)
• Audio system: PortAudio (usually pre-installed)

Platform Support

• ✅ Linux (Full support)
• ✅ macOS (Full support)
• ⚠️ Windows (Limited - requires WSL or compatible terminal)

Configuration ⚙️

Environment Variables

• GEMINI_API_KEY - Your Google Gemini API key (required)

Audio Settings

The app automatically detects your default microphone. For advanced audio configuration, modify the AudioConfig class in silent_speech/main.py.

Controls 🎮

Key	Function
SPACE	Start/Stop recording
Q	Quit application
C	Copy last response
A	Toggle auto-copy
ESC	Quit application

API Key Setup 🔑

1. Visit Google AI Studio
2. Create a new API key
3. Set the environment variable:

   # Linux/macOS
   echo 'export GEMINI_API_KEY="your-key-here"' >> ~/.bashrc
   source ~/.bashrc
   
   # Or for current session only
   export GEMINI_API_KEY="your-key-here"
   

Troubleshooting 🔧

Common Issues

"No audio input detected"

• Check microphone permissions
• Verify microphone is connected and working
• Try running: python -c "import sounddevice; print(sounddevice.query_devices())"

"Gemini API key not found"

• Ensure GEMINI_API_KEY environment variable is set
• Verify the API key is valid and active

"Module 'tty' has no attribute 'cbreak'"

• This typically occurs on Windows. Use WSL or a Unix-compatible terminal

Audio dependency issues

• Install system audio libraries:

  # Ubuntu/Debian
  sudo apt-get install portaudio19-dev python3-pyaudio
  
  # macOS
  brew install portaudio
  

Development 🛠️

Local Development

git clone https://github.com/laspencer91/silent-speech.git
cd silent-speech
pip install -e .
silent-speech

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License 📄

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments 🙏

• Google Gemini AI for speech transcription
• Rich Library for beautiful terminal UI
• SoundDevice for audio capture
• All contributors and users!

Support 💬

• 🐛 Issues: GitHub Issues
• 💡 Feature Requests: GitHub Discussions
• 📧 Contact: [e-mail]

---

Made with ❤️ by the Silent Speech Team