Type alias AgentSessionOptions<UserData>

Type declaration

• Optional aecWarmupDuration?: number | null

  Duration in milliseconds for AEC (Acoustic Echo Cancellation) warmup, during which interruptions from audio activity are suppressed. Set to null to disable.

  Default Value

  3000
  Copy

• Optional connOptions?: SessionConnectOptions

• Optional llm?: llm.LLM | llm.RealtimeModel | LLMModels

• Optional maxToolSteps?: number

• Optional preemptiveGeneration?: boolean

  Whether to speculatively begin LLM and TTS requests before an end-of-turn is detected. When true, the agent sends inference calls as soon as a user transcript is received rather than waiting for a definitive turn boundary. This can reduce response latency by overlapping model inference with user audio, but may incur extra compute if the user interrupts or revises mid-utterance.

  Default Value

  true
  Copy

• Optional stt?: stt.STT | STTModelString

• Optional tts?: tts.TTS | TTSModelString

• Optional turnDetection?: TurnDetectionMode

  Deprecated

  use turnHandling.turnDetection instead

• Optional turnHandling?: Partial<TurnHandlingOptions>

  Configuration for turn handling.

• Optional useTtsAlignedTranscript?: boolean

• Optional userAwayTimeout?: number | null

  If set, set the user state as "away" after this amount of time after user and agent are silent. Set to null to disable.

  Default Value

  15.0
  Copy

• Optional userData?: UserData

• Optional vad?: VAD

• Optional voiceOptions?: Partial<VoiceOptions>

  Deprecated

  use top-level SessionOptions fields instead