A powerful AI-driven web application built with Streamlit that automatically extracts YouTube video transcripts and generates intelligent summaries using Groq's LLaMA 3.1 model. Transform long videos into concise, actionable insights in seconds!
- Automatic transcript extraction using
yt-dlpfor reliable video processing - Multi-language support for videos with available captions
- Robust error handling for private videos and missing transcripts
- Real-time processing with live progress indicators
- Groq LLaMA 3.1-8B integration for high-quality summaries
- 4 Summary Styles:
- π General Summary - Comprehensive overview
- π Detailed Summary - In-depth analysis with key points
- π Bullet Points - Quick, scannable format
- π― Key Takeaways - Essential insights and action items
- Smart text chunking for videos of any length (handles token limits automatically)
- Customizable parameters for advanced users
- Beautiful gradient design with dark/light mode support
- Responsive layout that works on all devices
- Interactive analytics showing word counts, compression ratios, and reading time
- One-click actions: Copy summary, download as text, or start over
- Expandable transcript viewer with proper formatting
- Real-time statistics: Original vs. summary word count
- Compression ratio showing efficiency gains
- Estimated reading time for quick planning
- Session analytics tracking your usage
- Python 3.8 or higher
- Groq API key (free tier available)
- Clone the repository
git clone https://github.com/bskrishna2006/Youtube-video-summarizer.git
cd Youtube-video-summarizer- Install dependencies
pip install -r requirements.txt- Set up environment variables
# Create .env file
echo "GROQ_API_KEY=your_groq_api_key_here" > .env- Run the application
streamlit run app.py- Open your browser and navigate to
http://localhost:8501
Create a .env file in the project root:
GROQ_API_KEY=your_groq_api_key_hereThe app includes customizable parameters for power users:
- Chunk Size: Adjust text processing size (default: 2500 chars)
- Max Summary Tokens: Control summary length (default: 500 tokens)
- Summary Style: Choose from 4 different formats
- Enter YouTube URL in the main input field
- Select summary style from the sidebar (optional)
- Click "π― Summarize Video" and wait for processing
- Review your summary with statistics and full transcript access
- Custom chunk sizes for handling very long videos
- Token limit adjustment for shorter/longer summaries
- Multiple summary formats for different use cases
- Session analytics to track your productivity
- Frontend: Streamlit with custom CSS for modern UI
- Video Processing:
yt-dlpfor reliable transcript extraction - AI Engine: Groq LLaMA 3.1-8B for natural language processing
- Text Processing: Smart chunking algorithm for large transcripts
youtube-video-summarizer/
βββ app.py # Main Streamlit application
βββ main.py # Command-line version
βββ requirements.txt # Python dependencies
βββ .env # Environment variables (create this)
βββ README.md # This file
βββ assets/ # Screenshots and images
- Summarize lecture videos for quick review
- Extract key concepts from educational content
- Create study notes from video lessons
- Process webinar recordings efficiently
- Extract action items from meeting recordings
- Analyze competitor presentations
- Research topics quickly from multiple videos
- Create content briefs from source material
- Analyze trending video content
- Process interview recordings
- Extract insights from conference talks
- Analyze video testimonials
We welcome contributions! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
# Clone your fork
git clone https://github.com/YOUR_USERNAME/Youtube-video-summarizer.git
# Install development dependencies
pip install -r requirements.txt
# Run tests (if available)
python -m pytest tests/This project is licensed under the MIT License - see the LICENSE file for details.
- Groq for providing excellent AI infrastructure
- Streamlit for the amazing web framework
- yt-dlp developers for reliable video processing
- LLaMA team for the powerful language model
- π Bug Reports: Open an issue
- π‘ Feature Requests: Start a discussion
- π§ Contact: Email
If you find this project helpful, please consider giving it a star! It helps others discover the project.
Made with β€οΈ by Krishna
Transform any YouTube video into actionable insights!