I'm here to help you with the issue of the agent continuing to speak after a user interruption and not taking into account what the user said. Let's go through some important steps together to get this working smoothly: • Enable Interruption Handling: Please check that

allow_interruptions

is set to

True

in your agent configuration. This setting helps the agent pause when the user interrupts. • Adjust Interruption Sensitivity: It might help to fine-tune parameters like

interrupt_speech_duration

and

interrupt_min_words

so the agent can better detect interruptions promptly. • Configure Voice Activity Detection (VAD): Make sure your VAD is properly set up to effectively pick up when the user speaks. • Handle Interruptions in Code: Using the

SpeechHandle

object to monitor interruptions and cancel ongoing tasks can make the agent more responsive. • Update Context After Interruption: It's important that the agent updates its conversation history to reflect only what the user actually heard, so the context stays accurate. • Process User Input Post-Interruption: Don’t forget to use the

user_input_transcribed

event to capture and respond to what the user says after interrupting. Following these steps should help your agent stop speaking promptly when interrupted and respond appropriately to user input. If you have any questions or need further assistance, feel free to reach out—I'm here to support you! Sources: Agent speech and audio | LiveKit Docs | pipeline-llm/interrupt_user.py | livekit-agents/livekit/agents/voice/agent_activity.py | VoicePipelineAgent | LiveKit Docs