---
title: "Transcribe audio"
method: POST
path: "/audio/transcriptions"
tags: ["Audio"]
---

# Transcribe audio

`POST /audio/transcriptions`

## Request

- Base URL: `https://api.munito.ai/inference/v1`
- URL: `https://api.munito.ai/inference/v1/audio/transcriptions`
- Auth: one of:
  - HTTP bearer
  - API key in header `x-api-key`

Turn speech into text with an audio model, in the request format of OpenAI's speech to text API. Set the OpenAI SDK base URL to https://api.munito.ai/inference/v1 and call `audio.transcriptions.create`.

- Send one file of WAV, MP3, FLAC, OGG, WebM, MP4 or M4A audio, at most 25 MB and 60 minutes long.
- Munito cuts a recording longer than 30 seconds at its quietest points, transcribes the clips, and joins their text in order.
- `response_format` is `json` (the default) or `text`. Timestamps, word log probabilities and streaming are not available.

The answer bills input and output tokens at the chat prices of the model. One second of audio is 25 input tokens, and `usage` gives the audio tokens apart from the text tokens of the instructions.

## Headers

- `munito-service-tier` 'priority' | 'standard' | 'flex'

## Request body `multipart/form-data`

- object
  - `file` string, binary, required: The audio file: WAV, MP3, FLAC, OGG, WebM, MP4 or M4A, at most 25 MB and 60 minutes.
  - `model` string, required: An audio model from GET /models, such as `google/gemma-4-12b`.
  - `language` string: The language of the audio as an ISO 639-1 code, such as `en` or `de`. Omit it to keep the language of the audio.
  - `prompt` string: Names and terms to spell correctly, at most 2,000 characters.
  - `response_format` 'json' | 'text': `json` gives the text and the token usage. `text` gives the plain text.
  - `temperature` number: Sampling temperature from 0 to 1. Omit it for 0.

## Response `200`

The text of the recording. With `response_format: text`, the body is the plain text.

## Other responses

- `400`: The request is outside the contract: an unknown field, a format other than `json` or `text`, timestamps, streaming, a language that is not supported, a model without audio, or a file that does not decode.
- `413`: The file is larger than 25 MB.
- `504`: The transcription did not finish in time. Send a shorter recording.

---

[API](https://skmtc.dev/munito/apis/munito-ai-api.md) - [All operations](https://skmtc.dev/munito/apis/munito-ai-api/llms.txt) - [OpenAPI document](https://skmtc.dev/munito/apis/munito-ai-api/revisions/d4ccbe8844df?raw)