Transcript object if job is succeeded, available for 24 hours after job completion
Show child attributes
Timestamp of the end of the inference
Timestamp of the start of the inference
Unique identifier of the transcript job
Language of the transcript. Either detected value if input was null or value is equal to user input. In form of ISO 639-1 code, like "en" or "de"
Number of speakers in the transcript. Either detected value if input was null or value is equal to user input
Array of segments, each segment contains spoken text, speaker, start and end time in seconds with decimal and a list of word objects (view below)
Average log probability of the segment
End time of the segment in seconds with decimal
Speaker of the segment
Start time of the segment in seconds with decimal
Spoken text of the segment
End time of the word in seconds with decimal
Probability of the word, can also be described as confidence score
Start time of the word in seconds with decimal
Spoken word
created
queued
running
succeeded
failed
