YouTube Summarizer Web Application

An AI-powered web application that automatically extracts, transcribes, and summarizes YouTube videos, providing intelligent insights and key takeaways.

🎯 Features

• Video Transcript Extraction: Automatically fetch transcripts from YouTube videos
• AI-Powered Summarization: Generate concise summaries using multiple AI models
• Multi-Model Support: Choose between OpenAI GPT, Anthropic Claude, or DeepSeek
• Key Points Extraction: Identify and highlight main topics and insights
• Chapter Generation: Automatically create timestamped chapters
• Export Options: Save summaries as Markdown, PDF, or plain text
• Caching System: Reduce API calls with intelligent caching
• Rate Limiting: Built-in protection against API overuse

🏗️ Architecture

[Web Interface] → [FastAPI Backend] → [YouTube API/Transcript API]
                         ↓
[AI Service] ← [Summary Generation] ← [Transcript Processing]
                         ↓
[Database Cache] → [Summary Storage] → [Export Service]

🚀 Quick Start

Prerequisites

• Python 3.11+
• YouTube API Key (optional but recommended)
• At least one AI service API key (OpenAI, Anthropic, or DeepSeek)

Installation

1. Clone the repository

git clone https://eniasgit.zeabur.app/demo/youtube-summarizer.git
cd youtube-summarizer

2. Set up virtual environment

python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. Configure environment

cp .env.example .env
# Edit .env with your API keys and configuration

5. Initialize database

alembic init alembic
alembic revision --autogenerate -m "Initial migration"
alembic upgrade head

6. Run the application

python src/main.py

The application will be available at http://localhost:8082

📁 Project Structure

youtube-summarizer/
├── src/
│   ├── api/              # API endpoints
│   │   ├── routes.py     # Main API routes
│   │   └── websocket.py  # Real-time updates
│   ├── services/         # Business logic
│   │   ├── youtube.py    # YouTube integration
│   │   ├── summarizer.py # AI summarization
│   │   └── cache.py      # Caching service
│   ├── utils/            # Utility functions
│   │   ├── validators.py # Input validation
│   │   └── formatters.py # Output formatting
│   └── main.py           # Application entry point
├── tests/                # Test suite
├── docs/                 # Documentation
├── alembic/             # Database migrations
├── static/              # Frontend assets
├── templates/           # HTML templates
├── requirements.txt     # Python dependencies
├── .env.example        # Environment template
└── README.md           # This file

🔧 Configuration

Essential Environment Variables

Variable	Description	Required
YOUTUBE_API_KEY	YouTube Data API v3 key	Optional*
OPENAI_API_KEY	OpenAI API key	One of these
ANTHROPIC_API_KEY	Anthropic Claude API key	is required
DEEPSEEK_API_KEY	DeepSeek API key	for AI
DATABASE_URL	Database connection string	Yes
SECRET_KEY	Session secret key	Yes

*YouTube API key improves metadata fetching but transcript extraction works without it.

🧪 Testing

Run the test suite:

pytest tests/ -v
pytest tests/ --cov=src --cov-report=html  # With coverage

📝 API Documentation

Once running, visit:

• Interactive API docs: http://localhost:8082/docs
• Alternative docs: http://localhost:8082/redoc

Key Endpoints

• POST /api/summarize - Submit a YouTube URL for summarization
• GET /api/summary/{id} - Retrieve a summary
• GET /api/summaries - List all summaries
• POST /api/export/{id} - Export summary in different formats

🚢 Deployment

Docker

docker build -t youtube-summarizer .
docker run -p 8082:8082 --env-file .env youtube-summarizer

Production Considerations

1. Use PostgreSQL instead of SQLite for production
2. Configure proper CORS settings
3. Set up SSL/TLS certificates
4. Implement user authentication
5. Configure rate limiting per user
6. Set up monitoring and logging

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

📄 License

This project is part of the Personal AI Assistant ecosystem.

🔗 Related Projects

• Personal AI Assistant
• YouTube Automation Service
• PDF Translator

📞 Support

For issues and questions, please create an issue in the repository.