A simple Python project that listens to your microphone, processes the speech, and responds using Text-to-Speech (TTS). CopyCat records audio from your microphone, converts it to text, processes the text (with special responses to phrases like "copy"), and generates a spoken reply using ElevenLabs' TTS API.
- Python 3.10+
- FFmpeg (Required for audio processing)
- Install via:
- macOS: `brew install ffmpeg`
- Linux: `sudo apt install ffmpeg`
- Windows: Download from [FFmpeg's official site](https://ffmpeg.org/)
- Clone the repository:
git clone https://github.com/yourusername/CopyCat.git
cd CopyCat- Install dependencies:
pip install -r requirements.txt- Add your ElevenLabs API key to a .env file:
ELEVENLABS_API_KEY=your_api_key_here
This project includes several exciting features for you to explore:
- Microphone recording: Real-time microphone recording (6-second clips).
- Speech-to-text conversion: Speech-to-text conversion via Google's Speech Recognition.
- Smart text processing: Copies what you say and provides special responses based on your input (e.g., replies "Ok I won't then" if you say "copy").
- TTS Responses: Natural-sounding TTS responses using ElevenLabs.
- Automatic responses: Plays responses aloud automatically.