Skip to main content

​
TurnDetector

End-of-turn detector; decides when the caller has finished speaking. Selected by model: 'echo-large' (the default) or 'echo-small'.

​
Constructor

​
model
TurnDetectorModel | string | null
Which detector to use: 'echo-large' (the default) or 'echo-small'. See TurnDetectorModel.
​
threshold
number
End-of-turn probability cutoff in [0, 1]. Default 0.7.
​
host
string | null
Inference service address. Falls back to the ZRT_INFERENCE_GATEWAY env var, then the default endpoint.
​
authToken
string | null
Inference service auth token. Default ''.
​
baseUrl
string | null
Inference service base URL. Default null.

​
cleanup

Tear down provider state.

​
close

Release any resources held by the provider.

​
closeEmitter

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

​
detectEndOfUtterance

Whether the current EOU probability meets threshold (or the configured one).
​
chatContext
any
​
threshold
number
​
returns
boolean

​
emit

​
event
string
required

​
getEouProbability

Latest end-of-utterance probability 0-1 (defaults to 0.5 when unknown).
​
returns
number

​
getRuntimeConfig

​
returns
Record<string, any>

​
listenerCount

​
event
string
required
​
returns
number

​
off

​
event
string
required
​
handler
EventHandler
required

​
on

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
once

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
removeAllListeners

​
event
string

​
setThreshold

Update the end-of-utterance threshold.
​
threshold
number
required