I totally understand how important it is to get this right! When you use

session.output.set_audio_enabled(false)

during an agent's speech, the audio output stops immediately, and any speech that's happening will be interrupted. This also means the agent’s voice will pause mid-sentence, and any speech waiting in the queue will be cleared. While the audio is off, the agent can still send transcribed text responses through the

lk.transcription

text stream topic, as long as text output is enabled. Just a heads-up, these text responses won’t have the

lk.transcribed_track_id

attribute, so they won’t sync up with audio playback. If you'd like, I’m here to help you set up your client to smoothly handle text responses when the audio is disabled—just let me know! Sources: Text and transcriptions | LiveKit Docs | Text and transcriptions | LiveKit Docs | livekit-agents/livekit/agents/voice/chat_cli.py | How to Set Up Speech-to-Text Input with Text-Only Output in LiveKit Agents | Docs::Agents

?