---
title: "Create Speech (Text-to-Speech)"
method: POST
path: "/v1/audio/speech"
tags: ["Audio"]
---

# Create Speech (Text-to-Speech)

`POST /v1/audio/speech`

Converts text to spoken audio using AI voice synthesis. Supports multiple voices, audio formats, and streaming capabilities.

## Request body

- SpeechRequest
  - `model` string, required — Model to use for speech synthesis in 'provider/model' format
  - `input` string, required — Text to convert to speech (max 4096 characters)
  - `voice` 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer', required — Voice to use for speech synthesis
  - `response_format` 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm' — Audio format for the response
  - `instructions` string — Additional instructions for voice synthesis
  - `stream_format` 'sse' — Enable streaming with Server-Sent Events

## Response `200`

Audio data or streaming response

## Other responses

- `400` — unresolved $ref
- `401` — unresolved $ref
- `429` — unresolved $ref
- `500` — unresolved $ref

---

[API](https://skmtc.dev/getbifrost/apis/bifrost-http-transport-api.md) · [All operations](https://skmtc.dev/getbifrost/apis/bifrost-http-transport-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/getbifrost/bifrost-http-transport-api/revisions/e70d3ae3c0d0/schema)