<<<<<<< HEAD

DebateMeAI

=======

🎭 DebateMe.AI

A real-time debate application where users can challenge AI opponents with different personalities using voice input and receive AI responses with text-to-speech.

🚀 Features

• Voice Recording: Record your arguments using your microphone
• Speech-to-Text: Transcribe speech using OpenAI Whisper
• AI Responses: Get intelligent responses from Google Gemini
• Text-to-Speech: Hear AI responses with gTTS
• Character Selection: Choose from different AI personalities:
  • 🤖 Logical Bot: Analytical and fact-based
  • 😈 Villain Bot: Aggressive and confrontational
  • 🤝 Supportive Bot: Empathetic and encouraging
  • 🧠 Philosopher Bot: Deep and contemplative
• Debate History: Track the conversation flow
• Scoring System: Basic scoring based on argument length
• Beautiful UI: Modern, responsive design with animations

📋 Prerequisites

• Python 3.8 or higher
• Microphone access
• Internet connection (for TTS and AI responses)

🛠️ Installation

1. Clone or download this project

   git clone <repository-url>
   cd debate

2. Install dependencies

   pip install -r requirements.txt

3. Set up API keys (you'll need these for full functionality):

   • Google Gemini API Key: Get from Google AI Studio
   • Create a .env file in the project root:

   GOOGLE_API_KEY=your_gemini_api_key_here
   

🎯 What You Need to Do Manually

1. Get Google Gemini API Key

• Go to Google AI Studio
• Create a new API key
• Add it to your .env file

2. Install FFmpeg (for Whisper)

• Windows: Download from FFmpeg website or use chocolatey: choco install ffmpeg
• Mac: brew install ffmpeg
• Linux: sudo apt install ffmpeg

3. Optional: Add Custom Avatars

• Create an avatars/ folder
• Add images for each character (PNG/JPG format)
• Update the character configurations in app.py

🚀 Running the App

streamlit run app.py

The app will open in your browser at http://localhost:8501

🎮 How to Use

1. Choose Your Opponent: Select a character from the sidebar
2. Record Your Argument: Click the microphone button and speak
3. Wait for Processing: The app will transcribe your speech and generate an AI response
4. Listen to Response: The AI will respond with text-to-speech
5. Continue the Debate: Keep the conversation flowing!

📁 Project Structure

debate/
├── app.py              # Main Streamlit application
├── requirements.txt    # Python dependencies
├── README.md          # This file
├── .env               # API keys (create this)
└── avatars/           # Custom avatar images (optional)

🔧 Technical Details

Current Implementation (Step 1)

• ✅ Voice recording with Streamlit's audio recorder
• ✅ Speech transcription with Whisper
• ✅ Basic AI responses (placeholder)
• ✅ Text-to-speech with gTTS
• ✅ Character selection and UI
• ✅ Debate history tracking
• ✅ Basic scoring system

Next Steps

• 🔄 Integrate Google Gemini API for intelligent responses
• 🔄 Add debate memory and context
• 🔄 Improve scoring algorithm
• 🔄 Add speaking animations
• 🔄 Custom avatar images
• 🔄 Real-time voice streaming

🐛 Troubleshooting

Common Issues:

1. "No module named 'whisper'"

   • Run: pip install openai-whisper

2. "FFmpeg not found"

   • Install FFmpeg (see installation section)

3. "No microphone access"

   • Allow microphone access in your browser
   • Check system microphone permissions

4. "API key error"

   • Make sure your .env file exists with the correct API key

🤝 Contributing

Feel free to contribute by:

• Adding new AI characters
• Improving the scoring system
• Enhancing the UI/UX
• Adding new features

📄 License

This project is open source and available under the MIT License.

---

Happy Debating! 🎭

f27cb38 (Initial commit)