Introduction - Avaturn.Live

Avaturn.Live renders a photo-realistic avatar driven by a real-time conversation engine. Mint a session on your backend, pass a short-lived token to the frontend, and the Web SDK streams the avatar over WebRTC.

How it works

Create a session

POST /api/v1/sessions with a conversation engine config. Returns session_id (backend) and token (frontend).

Connect

Pass token to the Web SDK. The avatar joins over WebRTC and starts conversing.

Terminate

DELETE /api/v1/sessions/{id}, or let it expire on idle.

Conversation engines

Engine	When	Configured
OpenAI Realtime	Low-latency voice-to-voice with inline prompts	Per session, ephemeral client secret
Cartesia	Voice-to-voice agents deployed on Cartesia Line	Per agent, in your Cartesia deployment

New integrations should use OpenAI Realtime — it’s the fastest path to a working voice-to-voice avatar. Cartesia is the right pick if your agent already lives on Cartesia Line.

A legacy text-echo flow (backend pushes text, avatar speaks it) is preserved under Legacy for existing integrations.

Start here

Quickstart

Voice-to-voice avatar in 5 minutes.

Web SDK

Render, devices, events, lifecycle.

REST API

Session lifecycle from your backend.

API Reference

Endpoints, schemas, errors.

Quickstart

​How it works

​Conversation engines

​Start here

Quickstart

Web SDK

REST API

API Reference

How it works

Conversation engines

Start here