Optional aec3000
Optional connOptional forwardMaximum time in milliseconds to wait for the next frame while forwarding TTS
audio to the audio output inside performAudioForwarding. Applies to every read,
including the first. If exceeded, forwarding is forcibly closed and a stall
warning is logged.
10000
Optional llm?: llm.LLM | llm.RealtimeModel | LLMModelsOptional maxOptional preemptiveUse turnHandling.preemptiveGeneration instead.
When set, migrated into turnHandling.preemptiveGeneration.enabled.
Optional stt?: stt.STT | STTModelStringOptional tts?: tts.TTS | TTSModelStringOptional ttsMaximum time in milliseconds to wait for the next frame on the TTS audio stream
inside performTTSInference. Applies to every read, including the first.
If exceeded, the TTS stream is forcibly closed and a stall warning is logged.
10000
Optional turnuse turnHandling.turnDetection instead
Optional turnConfiguration for turn handling.
Optional useOptional userIf set, set the user state as "away" after this amount of time after user and agent are
silent. Set to null to disable.
15.0
Optional userOptional vad?: VADOptional voiceuse top-level SessionOptions fields instead
Duration in milliseconds for AEC (Acoustic Echo Cancellation) warmup, during which interruptions from audio activity are suppressed. Set to
nullto disable.