Interface: SegmentDecoded

Properties

confidence

confidence: number

Confidence score between 0.0 and 1.0.


end

end: number

Timestamp of the end of the word, in milliseconds.


lang

lang: string

Speech language. 2 letter ISO code.


length

length: number

Length of the word, in milliseconds.


model

model: string

Technical name of ASR model. You can find the list of available models here.


speaker

speaker: string

The id of the speaker.


start

start: number

Timestamp of the beginning of the word, in milliseconds.


transcript

transcript: string

Concatenated words of the segment.


utterance_id

utterance_id: number

Identifies the utterance this event transcribes.


words

words: SegmentDecodedWord[]

Words decoded for the segment.