---
title: "OpenAI Compatible - Create Speech"
method: POST
path: "/openai/v1/audio/speech"
tags: ["OpenAI Integration", "Audio"]
---

# OpenAI Compatible - Create Speech

`POST /openai/v1/audio/speech`

OpenAI-compatible speech synthesis endpoint. Drop-in replacement for OpenAI's audio/speech API with identical request/response format.

## Request body

- OpenAISpeechRequest
  - `model` 'tts-1' | 'tts-1-hd', required — TTS model to use
  - `input` string, required — Text to generate audio for (max 4096 characters)
  - `voice` 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer', required — Voice to use when generating the audio
  - `response_format` 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm' — Format to audio in
  - `speed` number — Speed of the generated audio (0.25 to 4.0)
  - `instructions` string — Additional instructions for voice synthesis
  - `stream_format` 'sse' — Enable streaming with Server-Sent Events

## Response `200`

Audio data

## 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)