amith33/voice_agent

Voice Agent Project

A powerful voice cloning and lip synchronization system that can generate talking head videos from text input and reference images.

Features

• —Voice Cloning: Generate speech from text using XTTS v2
• —Lip Synchronization: Create realistic talking head videos using SadTalker
• —Web Interface: Easy-to-use FastAPI web application
• —GPU Acceleration: Optimized for GPU processing

Quick Start

Local Development

1. 1.Clone the repository
2. 2.Install dependencies: pip install -r requirements.txt
3. 3.Run the application: python app.py
4. 4.Open http://localhost:8000 in your browser

Hugging Face Spaces Deployment

This project is configured for deployment on Hugging Face Spaces using Docker SDK.

Hugging Face Spaces Configuration

title: Voice Agent Project
emoji: 🎭
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 8000
app_file: app.py

API Endpoints

• —GET / - Web interface
• —GET /health - Health check
• —GET /api/health - API health check
• —POST /upload-image - Upload source image
• —POST /generate - Generate video with voice cloning and lip sync
• —GET /status - Check processing status
• —GET /video/{filename} - Download generated video

Model Downloads

The application automatically downloads required models on first use:

• —SadTalker models for lip synchronization
• —XTTS v2 models for voice cloning

Hardware Requirements

• —Recommended: GPU with CUDA support
• —Minimum: 8GB RAM, 4GB VRAM
• —Storage: 10GB+ for models and temporary files

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.