Learn how to configure the STT layer to enable smart turn detection and enhance conversational flow.
smart_turn_detection
, powered by Sparrow, for dynamic and responsive conversation flow with intelligent turn-taking.
layers.stt
object. Below are the parameters available:
stt_engine
tavus-advanced
(default) – Offers high-accuracy multilingual transcription.tavus-turbo
– Provides faster response times with slightly reduced accuracy.participant_pause_sensitivity
high
: The replica replies quickly after short pauses. Good for fast and casual conversations.medium
(default): Balanced timing. Allows natural pauses without feeling rushed or delayed.low
: The replica waits a bit longer before replying. Useful for slower or more thoughtful discussions.verylow
: The replica allows even longer pauses before responding.superlow
: The replica has the longest response delay, making it suitable for conversations where participants often pause.participant_interrupt_sensitivity
high
: The replica stops speaking immediately when the participant starts talking. Ideal for quick and back-and-forth exchanges.medium
(default): Balanced behavior. Allows short interruptions without breaking the flow.low
: The participant needs to speak more clearly or for a bit longer to interrupt.verylow
: The replica usually keeps talking unless the interruption is strong.superlow
: The replica rarely stops mid-sentence. It will usually finish speaking before responding.hotwords
tavus-advanced
engine.Turn-taking model
smart_turn_detection
is only supported by the tavus-advanced
engine.smart_turn_detection
turns off Sparrow and uses a fixed response delay based on participant_pause_sensitivity
.