hanutchu

AI Speech Interactive Web Application

An interactive web application that enables real-time speech recognition and AI-powered responses, creating a seamless voice-based interaction between users and AI.

🌟 Features

• Real-time speech recognition using whisper.cpp
• Natural language processing with AI model integration
• Voice synthesis for AI responses (Kokoro/ F5 TTS)
• Responsive web design for all devices
• Low-latency communication
• Simple and intuitive user interface

🚀 Quick Start

1. Clone the repository:

git clone https://github.com/erturkkadir/hanutchu.git
cd hanutchu

🛠️ Technology Stack

• Frontend: vanilla js
• Speech Recognition: whisper.cpp
• Voice Synthesis: vioce activity detection
• AI Integration: ollama with any model
• Styling: Bootstrap CSS
• Development: Python. Websokcet/WebRTC,

🔧 System Requirements

• Modern web browser with microphone and.or webcam
• Active internet connection

📖 How It Works

1. Speech Recognition: The application listens to user speech input using basic browser functions
2. Text Processing: Converts speech to text and processes it for AI model consumption
3. AI Processing: Sends processed text to AI model and receives response
4. Voice Synthesis: Converts AI response to speech using S2T model (kokoro, F5)
5. User Interface: Updates UI with transcription and response in real-time

🤝 Contributing

We welcome contributions! Please follow these steps:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Development Guidelines

• Follow the existing code style and conventions
• Write clear commit messages
• Add tests for new features
• Update documentation as needed

📝 License

This project is licensed under the Apacahe 2.0 License - see the LICENSE file for details.

🎯 Roadmap

• Add support for multiple languages
• Implement conversation history
• Add voice customization options
• Create offline mode capabilities
• Improve error handling and recovery
• Add unit and integration tests

🤔 Support

If you encounter any issues or have questions:

1. Check the Issues page
2. Create a new issue if your problem isn't already listed
3. Join our Discord community

🙏 Acknowledgments

• llama.cpp / whisper.cpp GGerganov for their amazing work
• ollama team for their excellent API
• All our contributors and supporters

---

Made with ❤️ by [KadirErturk]