Discussions

Is there an option to display the avatar as a still image to be used while the avatar is idle?
What are people doing to avoid usage when the avatar needs to be displayed on a page before the user starts the stream.
We use static images, then replace them with the stream once the user clicks play to interact and I am wondering if there is a cleaner option

first question: is in fullmode im getting livkit url and token from which i can join the room and chat with avatar then how do i record the session like whole screen.typical recording in teams or google meet.
second question: im using full mode can i pass my own knowledge base if yes then how is context api is the same as knowledge base?
third question: if i have to use custom mode i have to setup my livkit room where avatar will join the meeting room but im not able to get audio using the wsurl i got from start session

I want to use LiveAvatar with LiveKit in Custom Mode and connect it to Gemini Live.
Do you have an official JavaScript / Node.js plugin or SDK for the LiveAvatar + LiveKit integration or the new LiveKit Avatar Plugin?
And if not, is it possible to build this pipeline using Node.js, or is it only supported in Python right now?

We’re integrating LiveAvatar FULL mode. /v1/sessions/start returns a livekit_url and livekit_client_token (identity is client). We connect with @livekit/react-native using
that token. Audio plays (we hear the avatar), but remoteParticipants is always empty and no trackSubscribed events fire, so we can’t render video. Logs show no participants
before disconnect. Sample start payload (token redacted):

Hi there,

"Stops a running session. If the session token from Create Session Token is used, we do not require a session token."

"When successful, you'll receive both a session_id and session_id." should probably read "When successful, you'll receive both a session_id and session_token.".

Does liveavatar currently support changing the background in stock and custom created avatars?

first question is in fullmode im getting livkit url and token from which i can join the room and chat with avatar then how do i record the session like whole screen.
second question im using full mode can i pass my own knowledge base if yes then how is context is the same as knowledge base?

Should my backend also join the livekit room with the same livekit_client_token?