Speech-to-Text REST API parameters

Reference of all parameters for the Telnyx Speech-to-Text REST API — audio source, language, model, diarization, punctuation, and response options.

All parameters are sent as multipart/form-data.

model · string · required

Model to use for transcription. See Models for details.

Values: openai/whisper-large-v3-turbo (default), openai/whisper-tiny, deepgram/nova-3, deepgram/nova-3-medical, deepgram/nova-2, deepgram/nova-2-medical, nvidia/parakeet-v3, omi-health/omi-med-stt-v1, reson8/prerecorded

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

Model options. The deepgram/* models take Deepgram’s options, including diarize and multichannel; reson8/prerecorded takes diarize and max_speakers. Returns 400 for other models. See Model Config.