Skip to main content
All parameters are sent as multipart/form-data.
​
model
string
required
Model to use for transcription. See Models for details.Values: distil-whisper/distil-large-v2 (default), openai/whisper-large-v3-turbo, deepgram/nova-3
​
file
file
Audio file to transcribe. Mutually exclusive with file_url. See Audio Formats for supported formats, size limits, and per-model restrictions.
​
file_url
string
Publicly accessible URL to an audio file. Mutually exclusive with file. See Audio Formats for details on how file and file_url differ.
​
language
string
Language hint. Behavior varies by model — see Language.
​
response_format
string
Output shape. See Response Format.Values: json (default), verbose_json
​
timestamp_granularities[]
string
Timestamp detail level. Only valid with response_format=verbose_json — returns 400 otherwise.Values: segment
​
model_config
object
Deepgram-specific options. Only valid with deepgram/nova-3 — returns 400 for other models. See Model Config.