A segment object represents a segment of audio that has been assigned a speaker label.

If a voiceprint was provided in the request, the speaker field will contain the label assigned to the voiceprint if a match was found.

start
number
required

Start time of the segment (in seconds) with decimal precision

end
number
required

End time of the segment (in seconds) with decimal precision

speaker
string
required

Speaker label. In form of SPEAKER_XX where XX is a number starting at 00. Or if a voiceprint was provided and a match found, the label is the name of the voiceprint.