AudioConfig
Conversation audio options.
See
Example
const conversation = application.createConversation(); conversation.audio.tts = "dasha"; // use Dasha's own STT engine conversation.audio.noiseVolume = 0.1; // lower the background noise volume
Indexable
[key: string]: unknown
Properties
interruptDelay?
optionalinterruptDelay:number
noiseVolume?
optionalnoiseVolume:number
Volume multiplier of the background noise applied to the AI audio track relative to the audio track.
Recommended value range is 0.1-0.3.
stt
stt:
SttProviderName
A speech-to-text provider to be used by the conversation.
Default
"default"
tts
tts:
TtsProviderName
A text-to-speech provider to be used by the conversation.
Default
"default"
vadPauseDelay?
optionalvadPauseDelay:number
Length of expected pause in seconds at the end of human speech.
Too big of a value will lead to long pauses before answer. Too small of a value will lead to errors in speech recognition.
vadStartupDelay?
optionalvadStartupDelay:number
Delay in seconds between executing the #connect method and starting of Voice Activity Detector.
It is necessary for the correct processing of the audio channel, due to the lack of data in the beginning of the audio track.