# FaceMode

> FaceMode turns voice agent audio into a real-time, lip-synced talking avatar and publishes it into the LiveKit or Daily.co room you already use.

## What FaceMode Does
- Takes audio from any voice pipeline (ElevenLabs, Cartesia, Deepgram, OpenAI, Gemini, Sarvam, Gnani, or custom)
- Generates lip-synced avatar video in real time (960ms target latency)
- Publishes the video as a participant in your LiveKit or Daily.co room
- Your app subscribes to the avatar's video track using the client SDK you already ship

## Integration Paths
1. **Plugin path** (for LiveKit Agents or Pipecat users): Install the plugin, keep writing agent code
   - `livekit-plugins-facemode` (Python, PyPI)
   - `@facemode/agents-plugin-facemode` (TypeScript, npm)
   - `pipecat-facemode` (Python, PyPI)
2. **Direct API path** (for everyone else): Create a session via REST, stream audio over WebSocket

## Pricing
- Credits-based: 1 credit = 1 second of avatar video
- Beta: 60 free minutes (3,600 credits), no card required

## Links
- Website: https://facemode.io
- Documentation: https://docs.facemode.io
- Console: https://console.facemode.io
- Company: https://infinitylevel.co