Making the web more accessible, one video at a time.
SignTube is an intelligent accessibility tool that automatically generates sign language animations for YouTube videos in real-time. By combining the power of OpenAI's Whisper for transcription and spaCy for NLP, we translate spoken English into grammatically correct American Sign Language (ASL), displayed via seamless overlays.
- 📺 Real-Time Translation: Instantly translates YouTube video audio into sign language.
- 🧠 Smart ASL Grammar: Not just word-for-word! Uses spaCy to reorder sentences into proper ASL structure (Time → Subject → Verb → Object).
- 🗣️ AI Transcription: Leverages OpenAI Whisper for state-of-the-art speech-to-text accuracy.
- 🔌 Browser Extension: A plug-and-play Chrome extension that integrates directly into the YouTube player.
- 🚀 Modern Web App: A beautiful Next.js frontend to explore and manage the platform.
- 🎭 3D & GIF Support: Uses a rich library of GIFs and 3D avatar fallbacks to ensure every word is signed.
- Framework: Next.js 16 & React 19
- Styling: Tailwind CSS v4
- Animations: Framer Motion & Canvas Confetti
- Extension: Manifest V3 (Chrome/Edge)
- Server: Python Flask
- AI/ML:
- OpenAI Whisper (Speech-to-Text)
- spaCy (NLP & Grammar Logic)
- Media Processing: yt-dlp & FFmpeg (Audio extraction)
The backend handles the heavy lifting of downloading audio, transcribing it, and processing the NLP.
cd backend
# Install dependencies
pip install -r requirements.txt
# Download the spacy model
python -m spacy download en_core_web_trf
# Run the server
python app.pyServer runs on http://localhost:5001
The web interface for the project.
cd frontend
# Install dependencies
npm install
# Run the dev server
npm run devApp runs on http://localhost:3000
- Open Chrome and go to
chrome://extensions/. - Enable Developer mode (top right).
- Click Load unpacked.
- Select the
extensionfolder in this repository. - Open a YouTube video and watch the magic happen! ✨
- /backend: Flask server, Whisper integration, and NLP logic.
- /frontend: Next.js web application.
- /extension: Chrome extension content scripts and manifest.
- /gif: Asset library for sign language visualizations.
- /animation: 3D animation assets.