response_format parameter.
json (Default)
Text only.
verbose_json
Adds duration (seconds) and timestamped segments — only when using deepgram/nova-3. The Whisper models (openai/whisper-large-v3-turbo, openai/whisper-tiny) return text only regardless of response_format. See the Timestamp Availability table below.
Example response with model=deepgram/nova-3:
timestamp_granularities[]=segment alongside response_format=verbose_json. Using timestamp_granularities without verbose_json returns 400.
Segment Fields
Timestamp Availability by Model
Streaming Response (Undocumented)
SendingAccept: application/stream+json returns newline-delimited JSON chunks as segments are transcribed. Each line: