> ## Documentation Index
> Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 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`.

<ParamField body="model" type="string" required>
  Model to use for transcription. See [Models](/docs/voice/stt/rest-api/parameters/models) for details.

  **Values:** `openai/whisper-large-v3-turbo` (default), `openai/whisper-tiny`, `deepgram/nova-3`
</ParamField>

<ParamField body="file" type="file">
  Audio file to transcribe. Mutually exclusive with `file_url`. See [Audio Formats](/docs/voice/stt/rest-api/parameters/audio-formats) for supported formats, size limits, and per-model restrictions.
</ParamField>

<ParamField body="file_url" type="string">
  Publicly accessible URL to an audio file. Mutually exclusive with `file`. See [Audio Formats](/docs/voice/stt/rest-api/parameters/audio-formats) for details on how `file` and `file_url` differ.
</ParamField>

<ParamField body="language" type="string">
  Language hint. Behavior varies by model — see [Language](/docs/voice/stt/rest-api/parameters/language).
</ParamField>

<ParamField body="response_format" type="string">
  Output shape. See [Response Format](/docs/voice/stt/rest-api/response).

  **Values:** `json` (default), `verbose_json`
</ParamField>

<ParamField body="timestamp_granularities[]" type="string">
  Timestamp detail level. Only valid with `response_format=verbose_json` — returns 400 otherwise.

  **Values:** `segment`
</ParamField>

<ParamField body="model_config" type="object">
  Deepgram-specific options. Only valid with `deepgram/nova-3` — returns 400 for other models. See [Model Config](/docs/voice/stt/rest-api/parameters/model-config).
</ParamField>