1
or 2
if using the dual_channel
option.
The confidence in the transcribed text, between 0.0 and 1.0.
Ending timestamp (in milliseconds) of the text in the transcript.
Speaker A
, Speaker B
, etc. if using the speaker_labels
option.
1
or 2
if using the dual_channel
option.
Starting timestamp (in milliseconds) of the text in the transcript.
The text of the utterance.
An array of the individual words in the utterance.
Generated using TypeDoc
A single "turn" in the conversation. A "turn" refers to a change in speakers. Only returned when using the
speaker_labels
ordual_channel
options.