Optional allowOptional chatOptional idOptional llmOptional llmProduces LLM chunks or text from the current chat and tool context.
Optional minOptional onCalled when the agent becomes active in a session.
Optional onCalled when the agent is leaving the active session.
Optional onCalled after the user's turn has been committed to the chat context.
Optional preserveOptional realtimeProcesses realtime model audio before it is sent to the agent output.
Optional sttOptional sttTransforms incoming audio into speech events or transcript text for the agent.
Optional toolOptional toolsOptional transcriptionTransforms the agent's output transcript before it is forwarded.
Optional ttsOptional ttsSynthesizes agent text into audio frames for playout.
Optional turnuse turnHandling.turnDetection instead
Optional turnOptional useOptional vad
Deprecated
use turnHandling.interruption.enabled instead