Interactive AI Avatar System with Real-time Streaming
Experience real-time interaction with an AI avatar. Speak naturally and watch the avatar respond with synchronized lip movements and voice.
BetaTechnical demonstration of WebRTC streaming capabilities, frame buffering, and real-time video processing.
OnlineCreate and customize your own AI avatars with different appearances, voices, and personalities.
Coming SoonQuick start guide, system requirements, and basic setup instructions for local development.
Complete guide for deploying on AWS EC2, including instance recommendations, scaling strategies, and optimization tips.
Comprehensive API documentation with endpoints, WebSocket events, and integration examples.
Live Swagger/OpenAPI documentation with try-it-out functionality for all endpoints.
LiveAvaTar uses a microservices architecture designed for scalability and real-time performance:
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Web Client │────▶│ FastAPI │────▶│ Redis Queue │
│ (JavaScript) │◀────│ Backend │◀────│ & Pub/Sub │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│ │ │
│ ▼ ▼
│ ┌─────────────────┐ ┌─────────────────┐
└─────────────▶│ WebSocket │ │ Linly-Talker │
│ Server │ │ (Lip Sync) │
└─────────────────┘ └─────────────────┘
# Clone the repository
git clone https://github.com/yourusername/AvaTar.git
cd AvaTar
# Start with Docker Compose
docker-compose -f docker-compose-simple.yml up -d
# Check health
curl http://localhost:8000/health
# Open demo
open http://localhost:8080