A powerful Python tool that transcribes and summarizes YouTube videos using OpenAI's Whisper for transcription and state-of-the-art language models for summarization.
- 🎯 Accurate Transcription: Uses OpenAI's Whisper model for high-quality speech-to-text conversion
- 📝 Smart Summarization: Generates concise, meaningful summaries using advanced language models
- 🌐 Flexible Model Options: Choose between local models or Hugging Face's API
- 🚀 Easy to Use: Simple command-line interface with sensible defaults
- 💾 Resource Efficient: Optimized for both high-end and resource-constrained systems
- Operating System: Linux, macOS, or Windows
- Python 3.10 or higher (if building from source)
- Internet connection (for model downloads and Hugging Face API)
- Download the appropriate binary for your system from the releases page
- Make the file executable (Unix systems):
chmod +x ytscript
- Move to a directory in your PATH:
sudo mv ytscript /usr/local/bin/
See our detailed build instructions for compiling from source code.
- Usage Guide - Learn about available commands and options
- Configuration Guide - Customize YTScript for your needs
# Basic transcription
ytscript "https://youtu.be/example" --model tiny
# Transcribe and summarize using a local model
ytscript "https://youtu.be/example" --summarize true
# Use Hugging Face for summarization
ytscript "https://youtu.be/example" --summarize true --summarizationModelType huggingface# Run all tests
make test
# Run specific test file
python -m pytest tests/test_transcription.py -v- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
This project is licensed under the GPL-3.0 License - see the LICENSE file for details.
- 📖 Check our documentation for detailed information
- 🐛 Report bugs in our issue tracker
- 💡 Request features in our discussions