FULL Mode Life Cycle

1. Starting a Session and connecting to the LiveKit Room

In FULL mode, you are able to configure and specify

• the avatar (via avatar_id)
• the avatar persona including
  • voice
  • context

See here for more details - https://docs.liveavatar.com/update/docs/full-mode-configurations.

Connecting and starting the session is otherwise the same process.

2. Managing the Session

In FULL mode, we will emit events on the whole state of the conversation. As such, via the client-side and server side events, you have access to:

• when the user/avatar is speaking.
• realtime transcript data on what the user/avatar is saying
• control over avatar behaviors such as:
  • interrupting
  • changing between idle and listening state
• direct control on what you want the avatar to say / respond to, in addition to processing user audio input.

See FULL mode's event list to see the up to date supported events

3. Ending the Session

When the session is closed, we will do the following.

• Close the LiveKit room
  • Our Avatar will leave the room and we will kick the user from the room if present.

While there are no resources that we expect the developers to manage, we also recommend cleaning up any resources that is used externally.