🚀 Transform Your Media Workflow with Python!
Discover a powerful toolkit designed for AI and tech enthusiasts looking to streamline video/audio content creation. Our cutting-edge solution harnesses WhisperX for transcription and Google’s Gemini API for proofreading and translation, delivering multilingual subtitles with precision.
Key Features:
- 🎯 High-quality transcription with word-level alignment using WhisperX
- 🔍 AI-powered proofreading through Gemini to correct errors
- 🌍 Multilingual support to broaden your audience
- 📥 Compatibility with various media sources: HLS streams, URLs, and local files
- 🎵 Audio fingerprinting via Shazam (macOS only)
- 📊 Comprehensive progress tracking with detailed terminal output
Getting Started:
- Ensure Python 3.10+ and FFmpeg installed.
- Clone the repo and quickly set up with just a few commands.
Join us on this innovative journey! Share your thoughts and experiences in the comments or share this post with your network! 🌍💬
