# FaceMode - Full Product Summary

> 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. Keep your voice stack. Add a face.
>
> FaceMode is operated by InfinityLevel (https://infinitylevel.co).

## What FaceMode Does

- Takes audio from any voice pipeline (ElevenLabs, Cartesia, Deepgram, Sarvam, Gnani, OpenAI, Gemini, or custom)
- Generates lip-synced avatar video in real time - 960ms target from audio to rendered frame
- Publishes the video as an ordinary participant in your LiveKit or Daily.co room
- Your app subscribes to the avatar's video track with the client SDK you already ship
- Output is 1K resolution video, delivered as one continuous stream - no render jobs, no polling

FaceMode does one job: it turns the audio your agent already produces into a talking avatar, in the room you already own. Your STT, LLM, TTS, and turn detection stay exactly where they are.

## How It Works

1. **Create a session** - One REST call returns the room binding and a one-time credential for the audio socket.
2. **Stream your audio** - Pipe the audio your agent already produces, about 100ms at a time. No client-side resampling.
3. **The face renders live** - FaceMode generates lip-synced video frames and publishes them into your room as an ordinary participant.
4. **Your app just watches** - Subscribe with the LiveKit or Daily.co client SDK you already ship. Nothing new on the frontend.

Pipeline: Audio in (from your TTS or agent) -> FaceMode (lip-synced video frames) -> Your room (LiveKit or Daily.co) -> On screen (your viewer SDK).

## Integration Paths

### Plugin path (LiveKit Agents or Pipecat)

Install the plugin and keep writing agent code. The plugin creates the session, opens the audio socket, and reconnects on drops.

- `livekit-plugins-facemode` (Python, PyPI)
- `@facemode/agents-plugin-facemode` (TypeScript, npm)
- `pipecat-facemode` (Python, PyPI)

### Direct API path (everything else)

Create a session over REST, open a WebSocket, stream audio. Any language that can hold a socket open works.

## Room Ownership

You own the room. You create a LiveKit or Daily.co room and hand FaceMode a token to join and publish. FaceMode never sits between your app and your room.

## Avatars

- Five art styles: realism, semi-realism, 3D animation, anime, flat vector
- Custom avatar: upload one front-facing portrait and it becomes an avatar
- Idle behavior: between utterances the avatar keeps blinking and breathing, then crossfades into speech. No freeze-frame, no state handling on your side.
- Interruption handling: people can cut in mid-sentence and the face keeps up (960ms audio-to-frame target)

## Pricing

- Credits-based pricing - 1 credit = 1 second of streamed avatar video
- No seats, no subscriptions
- Beta: 60 free minutes (3,600 credits), no card required
- Credit top-ups open at general availability

## FAQ

**Do I have to change my voice stack?**
No. FaceMode takes the audio your stack already produces. Your STT, LLM, TTS, and turn detection stay exactly where they are.

**Who owns the room?**
You do. You create a LiveKit or Daily.co room and hand FaceMode a token to join and publish. FaceMode never sits between your app and your room.

**I am already on LiveKit Agents or Pipecat.**
Install the plugin. It creates the session, opens the audio socket, and reconnects on drops. Python and JS for LiveKit Agents, Python for Pipecat.

**I am on neither.**
Create a session over REST, open a WebSocket, stream audio. Any language that can hold a socket open works.

**Can people interrupt the avatar?**
Yes. Stop sending audio and the face crossfades back into its idle loop instead of freezing, then picks straight back up.

**Can I use my own face?**
Upload one front-facing portrait and it becomes an avatar. Or pick from the library across five art styles.

**How does billing work?**
Credits, not seats or subscriptions. One credit is one second of streamed avatar video. FaceMode is in beta - top-ups for extra credits open once we hit general availability.

## Links

- Website: https://facemode.io
- Documentation: https://docs.facemode.io
- Console: https://console.facemode.io
- API: https://api.facemode.io
- Privacy Policy: https://facemode.io/privacy
- Terms: https://facemode.io/terms
- Company: https://infinitylevel.co