🎙️ AI Voice Chatbot

An interactive voice-enabled chatbot that uses the Hugging Face Inference API with Zephyr 7B Beta model for natural language processing. This application provides a seamless voice and text-based chat interface built with Python and Gradio.

✨ Features

• 🎤 Real-time voice recognition using SpeechRecognition library
• 💬 Text-based chat interface with conversation history
• 🔊 Text-to-speech using macOS native 'say' command
• 🎙️ Background listening with noise adjustment
• 🌐 Hugging Face Inference API integration with Zephyr 7B Beta model
• 🚀 Fast and responsive web interface built with Gradio
• 🔒 Secure API key management with python-dotenv
• 📦 Easy installation with pip

🛠️ Prerequisites

• Python 3.8 or higher
• macOS (required for native text-to-speech)
• Microphone (for voice input)
• Speakers or headphones (for voice output)
• Internet connection (for Hugging Face API)
• Hugging Face account (to get API key)

📝 Environment Setup

1. Get a Hugging Face API Key

   • Create an account at Hugging Face if you don't have one
   • Go to your profile → Settings → Access Tokens
   • Create a new token with read access

2. Set up environment variables Create a .env file in the root directory and add your Hugging Face API key:

   HUGGINGFACE_API_KEY=your_api_key_here

   Replace your_api_key_here with the token you obtained from Hugging Face.

🚀 Installation

1. Clone the repository

   git clone https://github.com/singlaamitesh/ChatBot.git
   cd ChatBot

2. Set up a virtual environment (recommended)

   # Create virtual environment
   python3 -m venv venv
   
   # Activate virtual environment
   # On macOS/Linux:
   source venv/bin/activate
   # On Windows:
   # .\venv\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

   This will install:

   • gradio: For the web interface
   • SpeechRecognition: For voice input processing
   • sounddevice & soundfile: For audio handling
   • python-dotenv: For environment variable management
   • huggingface-hub: For interacting with Hugging Face models

🏃‍♂️ Running the Application

1. Start the application

   python app.py

   The application will start and provide a local URL (typically http://localhost:7860).

2. Using the Chatbot

   • Voice Chat Tab:

     1. Click the microphone button
     2. Speak clearly into your microphone
     3. Click "Stop" when finished speaking
     4. The AI will process your speech and respond with both text and speech

   • Text Chat Tab:

     1. Type your message in the text box
     2. Press Enter or click "Send"
     3. The AI will respond with both text and speech

   • Clear Conversation: Use the "Clear Conversation" button to start a new chat session

3. Troubleshooting

   • If you encounter any issues, make sure:
     • Your microphone is properly connected and allowed in system preferences
     • You have a stable internet connection
     • Your Hugging Face API key is correctly set in the .env file

🎯 Example Commands

Try these voice or text commands:

• "Hello!" or "Hi"
• "How are you?"
• "What's your name?"
• "Tell me a joke"
• "Thank you"
• "Goodbye"
• "What's the weather like today?"

🛠️ Troubleshooting

Common Issues

1. Microphone Access

   • On macOS, go to System Preferences > Security & Privacy > Microphone
   • Ensure your browser or terminal has microphone access
   • Test your microphone with other applications first

2. Hugging Face API Errors

   • Verify your API key in the .env file
   • Check your Hugging Face account for valid tokens
   • Ensure you have sufficient credits/quota for the Zephyr 7B Beta model

3. Installation Issues

   # If you get port conflicts (port 7860 in use):
   # Option 1: Change the port in app.py
   # Option 2: Kill existing processes
   lsof -i :7860  # Find the process ID
   kill -9 <PID>  # Replace <PID> with the actual process ID

4. Audio Playback

   • Ensure your system volume is up and not muted
   • Check sound output device settings
   • The application uses macOS native say command - verify it works in terminal

Getting Help

If you encounter any issues not covered here, please:

1. Check the Issues page
2. Include details about:
   • Your operating system version
   • Python version (python --version)
   • Any error messages received
   • Steps to reproduce the issue
   • Monitor API usage limits

📝 Customization

Changing the AI's Personality

The chatbot uses the Zephyr 7B model from Hugging Face. You can modify the system prompt in app.py:

def generate_response(user_input):
    conversation_history.append(f"User: {user_input}")
    prompt = "<|system|>\nYou are a helpful AI assistant. Keep responses concise and natural for voice interaction.</s>\n"
    # Add your custom system prompt here

Adding New Features

• Customize voice settings: Modify the text_to_speech function to use different voices or adjust speaking rate
• Enhance speech recognition: Adjust recognizer settings in process_audio function
• Add new models: Integrate different Hugging Face models by updating the API endpoint
• Save conversation history: Add functionality to persist conversations to a database

📄 License

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

🙏 Acknowledgments

• Gradio for the easy-to-use web interface
• SpeechRecognition for speech-to-text capabilities
• Hugging Face for the Zephyr 7B model and Inference API
• MacOS say command for text-to-speech on macOS

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your 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