Interface: SegmentDecoded

Properties

confidence

• confidence: number

Confidence score between 0.0 and 1.0.

country

• country: string

Country where the speaker is (2 letters ISO 3166-1 code).

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.