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

# POST /v1/audio/speech

`POST /v1/audio/speech`

Generate a speech completion synchronously using the provided input text and model parameters.

## Request body

- object — Standard OpenAI speech generation response containing the generated speech and metadata.
  - `model` 'Chatterbox', required
  - `stream` boolean
  - `input` string, required
  - `voice` union — One of default voices: leo, nora or a file_id with purpose voice.
    - 'leo' | 'nora'
    - string
  - `temperature` number
  - `exaggeration` number
  - `cfg_weight` number
  - `response_format` 'wav'

## Response `200`

Default Response

- object[]
  - `url` string

## Other responses

- `400` — Default Response
- `404` — Default Response
- `500` — Default Response

---

[API](https://skmtc.dev/distribute/apis/distribute-ai-api.md) · [All operations](https://skmtc.dev/distribute/apis/distribute-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/distribute/distribute-ai-api/revisions/c00f2aec7fca/schema)