Update README.md

README.md

@@ -1,14 +1,117 @@
+# 🎤 Voice Agent with MCP - Gradio Hackathon
+
+**Hackathon Submission**: Gradio Agents & MCP Hackathon
+
+A lightweight voice agent that combines Gradio, ElevenLabs, and MCP (Model Context Protocol) to create an intelligent assistant capable of answering questions and scheduling calendar appointments.
+
+## 🚀 Features
+
+- **🗣️ Voice Input/Output**: Natural speech interaction using speech recognition and ElevenLabs TTS
+- **📅 Calendar Management**: Schedule appointments with natural language
+- **❓ Question Answering**: Handle general inquiries and provide helpful responses
+- **🔧 MCP Integration**: Uses Model Context Protocol for intelligent request processing
+- **⚡ Lightweight**: Optimized for Hugging Face Spaces deployment
+
+## 🛠️ Technology Stack
+
+- **Gradio**: Web interface and app framework
+- **ElevenLabs API**: High-quality text-to-speech synthesis
+- **MCP**: Model Context Protocol for intelligent processing
+- **Speech Recognition**: Voice-to-text conversion
+- **Python**: Backend processing and API integration
+
+## 🎯 Use Cases
+
+### Voice Interactions
+- "Hello, how are you today?"
+- "What time is it right now?"
+- "Schedule a doctor appointment for tomorrow at 3pm"
+- "Book a meeting with the team next Monday"
+
+### Calendar Management
+- Natural language appointment scheduling
+- Time and date extraction
+- Meeting type detection
+- Automatic event creation (demo mode)
+
+## 🔧 Setup Instructions
+
+### Environment Variables
+Set these in your Hugging Face Space settings:
+
+```bash
+ELEVENLABS_API_KEY=your_elevenlabs_api_key_here
+GOOGLE_CALENDAR_CREDENTIALS=your_google_credentials_json (optional)
+```
+
+### Local Development
+1. Clone the repository
+2. Install dependencies: `pip install -r requirements.txt`
+3. Set environment variables
+4. Run: `python app.py`
+
+## 📋 Requirements
+
+```
+gradio==4.44.0
+speechrecognition==3.10.0
+requests==2.31.0
+aiohttp==3.9.1
+python-dateutil==2.8.2
+pyaudio==0.2.11
+pydub==0.25.1
+```
+
+## 🎮 How to Use
+
+1. **Voice Mode**: 
+   - Click the microphone to record your voice
+   - Speak your question or appointment request
+   - Listen to the AI response
+
+2. **Text Mode**:
+   - Type your message in the text box
+   - Use quick action buttons for common requests
+   - View the AI's text response
+
+## 🔍 Architecture
+
+The agent uses a simple but effective architecture:
+
+1. **Input Processing**: Speech-to-text or direct text input
+2. **Intent Detection**: Determines if request is calendar-related or general Q&A
+3. **MCP Processing**: Routes requests through appropriate handlers
+4. **Response Generation**: Creates contextual responses
+5. **Output**: Text-to-speech or text display
+
+## 📈 Future Enhancements
+
+- Integration with real Google Calendar API
+- Advanced NLP for better appointment extraction
+- Multi-language support
+- Voice activity detection
+- Persistent conversation memory
+- Integration with additional calendar providers
+
+## 🏆 Hackathon Goals
+
+This project demonstrates:
+- **Gradio Integration**: Clean, intuitive web interface
+- **Voice Interaction**: Natural speech input/output
+- **MCP Implementation**: Intelligent request routing
+- **Practical Application**: Real-world calendar management
+- **Lightweight Design**: Optimized for cloud deployment
+
+## 🤝 Contributing
+
+This is a hackathon project, but feedback and suggestions are welcome!
+
+## 📄 License
+
+MIT License - Feel free to use and modify for your own projects.
+
 ---
-title: VoiceSupportAgent
-emoji: 🏆
-colorFrom: pink
-colorTo: blue
-sdk: gradio
-sdk_version: 5.33.0
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: 'A Voice Support Agent '
----
+
+**Built for the Gradio Agents & MCP Hackathon** 🚀
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference