---
title: "Create speech (OpenAI TTS)"
method: POST
path: "/openai/v1/audio/speech"
tags: ["OpenAI Integration"]
---

# Create speech (OpenAI TTS)

`POST /openai/v1/audio/speech`

Generates audio from text using OpenAI TTS.
Supports streaming via SSE when stream_format is set to 'sse'.

**Note:** This endpoint also works without the `/v1` prefix (e.g., `/openai/audio/speech`).

## Request body

- OpenAISpeechRequest
  - `model` string, required — Model identifier (e.g., tts-1, tts-1-hd)
  - `input` string, required — Text to convert to speech
  - `voice` 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' — Voice to use
  - `response_format` 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm'
  - `speed` number
  - `stream_format` 'sse' — Set to 'sse' for streaming
  - `fallbacks` string[]

## Response `200`

Successful response

## Other responses

- `400` — Bad request
- `500` — Internal server error

---

[API](https://skmtc.net/getbifrost/apis/bifrost-api.md) · [All operations](https://skmtc.net/getbifrost/apis/bifrost-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getbifrost/bifrost-api/versions/f8cab88f64ea/schema)