This project enables voice-based conversations with ChatGPT, allowing users to speak to the AI and receive spoken responses. It is designed for individuals seeking a more natural, hands-free interaction with large language models.

How It Works

The system captures audio input via a microphone, converts speech to text using an underlying LLM API, processes the text with ChatGPT, converts ChatGPT's text response back to speech, and plays the audio output. This creates a continuous, spoken dialogue loop.

Quick Start & Requirements

• Install Ubuntu dependencies: sudo apt install portaudio19-dev python3-pyaudio ffmpeg espeak
• Install Python requirements: pip install -r requirements.txt
• Configure API access by copying config.json.example to config.json and adding a session_token.
• Run the application: python chatgpt.py

Highlighted Details

• Voice-based interaction with ChatGPT.
• Real-time speech-to-text and text-to-speech.
• Designed for continuous conversation flow.

Maintenance & Community

No specific community channels, roadmap, or contributor information is provided in the README.

Licensing & Compatibility

The project's license is not specified in the README.

Limitations & Caveats

The project is currently command-line based and lacks a web interface. Future development plans include adding interruption capabilities, suppressing audio errors, filtering common AI phrases, and optimizing performance with GPU acceleration for speech-to-text.