Thanks — I understand you want the agent automatically muted whenever a participant with identity

claim_admin

joins a room. Below are concise, actionable examples and guidance for both Python and Node.js using the agent session's event hook and

set_audio_enabled

to disable the agent's audio output. What I'll cover: • Listen for the participant-connected event • Check the participant identity for

claim_admin

• Mute the agent with

session.output.set_audio_enabled(False)

(or

false

in JS) Python example

@server.rtc_session()
async def entrypoint(ctx: JobContext):
    session = AgentSession(
        # your model/STT/TTS settings
    )
    await session.start(agent=MyAgent(), room=ctx.room)

    def on_participant_connected(participant: rtc.RemoteParticipant):
        if participant.identity == "claim_admin":
            session.output.set_audio_enabled(False)  # mute agent

    ctx.room.on("participant_connected", on_participant_connected)
    await ctx.connect()

Node.js / TypeScript example

import { voice } from '@livekit/agents';

export default defineAgent({
    entry: async (ctx: JobContext) => {
        const session = new voice.AgentSession({
            // your model/STT/TTS settings
        });
        await session.start({ agent: new MyAgent(), room: ctx.room });

        ctx.room.on('participantConnected', (participant) => {
            if (participant.identity === 'claim_admin') {
                session.output.setAudioEnabled(false); // mute agent
            }
        });

        await ctx.connect();
    }
});

Notes and optional behavior • To unmute later, call

session.output.set_audio_enabled(True)

in Python or

session.output.setAudioEnabled(true)

in JS. • If you need to mute only specific agent voices or conditionally (e.g., only during certain times), you can add more checks inside the handler before calling

set_audio_enabled

. • If your environment emits a slightly different event name, confirm the room event for participant connection and adapt the handler name accordingly. If you want, tell me which language/environment you’re using and whether you want the agent to automatically unmute later (and when), and I’ll provide the exact code snippet to match that behavior. Sources: Text and transcriptions | LiveKit Documentation