<<<<<<< HEAD

LipSync Pro

AI-powered lip synchronization system with hybrid fast/quality path processing.

Features

• Hybrid Architecture: Fast preview (100-200ms) + High quality background processing
• MediaPipe: 468-point face mesh extraction
• Rhubarb: Audio-to-viseme conversion
• TPS Warping: Smooth mouth animation
• Supabase: Avatar and job management
• WebSocket: Real-time progress updates

Quick Start

Docker (Recommended)

# Copy environment
cp .env.example .env
# Edit .env with your keys

# Start all services
docker-compose up -d

Local Development

# Backend
cd backend
python -m venv venv
venv\Scripts\activate  # Windows
pip install -r requirements.txt
uvicorn app.main:app --reload

# Frontend
cd frontend
npm install
npm run dev

Usage

1. Open http://localhost:3000
2. Upload avatar video
3. Upload audio or record
4. Wait for processing
5. Download result

API Docs

http://localhost:8000/docs

Architecture

User → Frontend → Backend → Gemini → Audio
                     ↓
              Fast Path (quick preview)
              Quality Path (TPS warping)
                     ↓
              Video Output → WebRTC

Requirements

• Python 3.10+
• Node.js 18+
• FFmpeg
• Rhubarb Lip-Sync
• Docker (optional)

License

MIT

test-1

5289e4f891927ee3b6e5f43828eedf713c852d8b