I’d love to help you understand this better! When

allowInterruption

is set to False, it means that the agent will finish speaking without being interrupted by any user speech. During this time, any user audio input is usually ignored to make sure the agent’s response comes through clearly and without confusion. If you’d like the user input to be taken into account right after the agent finishes speaking, you can set

discard_audio_if_uninterruptible

to False. Also, if you want to allow interruptions manually, you can use the

interrupt()

method. Please feel free to ask if you want me to explain anything further or if you need help adjusting these settings—I’m here for you! Sources: VoicePipelineAgent | LiveKit Docs | VoicePipelineAgent | LiveKit Docs | Turn detection and interruptions | LiveKit Docs | livekit-agents/livekit/agents/voice/events.py | basics/interrupts_user.py