Initiate Room
OpenClaw
Initiate Room
Create a LiveKit room for an avatar session and receive a client join token
POST
Initiate Room
Documentation Index
Fetch the complete documentation index at: https://docs.agenthuman.com/llms.txt
Use this file to discover all available pages before exploring further.
What This Does: Creates a LiveKit room and returns the WebSocket URL and a JWT token your client can use to join immediately. The avatar agent connects automatically when the client joins.
Body
All fields are optional. When omitted, server-side defaults are used.Avatar ID to use for the session (e.g.
avat_01KMZHXFPBVCXA5ATK85HCP8G1). Must be an avat_... ID returned by the Upload Face endpoint.Video aspect ratio. Must be one of:
1:1, 4:3, 3:4. Defaults to 1:1.ElevenLabs voice ID to use for TTS. Defaults to the server-configured voice.
Whether to enable real-time transcription of user speech. Defaults to
true.Response
true when the room was created successfully.Room connection details.
How It Works
- A LiveKit room is created and configured with the options you provide.
- A client join token is generated.
- When the client connects using the returned
url+token, the avatar agent starts automatically.
No separate session call needed. Unlike the
/v1/sessions endpoint (which requires you to bring your own LiveKit room), this endpoint handles room creation for you. The avatar agent starts automatically on client join.