---
title: "Speech"
method: POST
path: "/v1/audio/speech"
tags: ["audio.speech"]
---

# Speech

`POST /v1/audio/speech`

Speech

## Request body

- SpeechRequest
  - `model` string, nullable
  - `metadata` MetadataDict — Custom type for metadata with embedded validation.
  - `stream` boolean
  - `prompt_cache_key` string, nullable
  - `voice_id` string, nullable — The preset or custom voice to use for generating the speech.
  - `ref_audio` union — The audio reference for generating the speech.
    - string
    - string
  - `input` string, required — Text to generate a speech from
  - `response_format` 'pcm' | 'wav' | 'mp3' | 'flac' | 'opus'

## Response `200`

Speech audio data.

- object
  - `audio_data` string, required — Base64 encoded audio data

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/mistral/apis/mistral-ai-api.md) · [All operations](https://skmtc.net/mistral/apis/mistral-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/mistral/mistral-ai-api/revisions/933c4ebdcd72/schema)