---
title: "Generate speech audio from text using the OpenAI SDK-compatible endpoint. Supports all AllModels TTS providers. Returns binary audio in the requested format (mp3, opus, aac, flac, wav, pcm)."
method: POST
path: "/allmodels/oai/audio/speech"
tags: ["AllModels"]
---

# Generate speech audio from text using the OpenAI SDK-compatible endpoint. Supports all AllModels TTS providers. Returns binary audio in the requested format (mp3, opus, aac, flac, wav, pcm).

`POST /allmodels/oai/audio/speech`

## Request

- Base URL: `https://api.orthogonal.com/mpp`
- URL: `https://api.orthogonal.com/mpp/allmodels/oai/audio/speech`
- Auth: none declared
- TypeScript: <https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/docs/allmodels/oai/audio/speech/post.ts> (a function with typed inputs; its response is checked against the schema)

## Request body

- object
  - `model` string, required: Model ID, e.g. 'elevenlabs/eleven_turbo_v2_5', 'deepgram/aura-2', 'cartesia/sonic'
  - `input` string, required: The text to generate audio for
  - `voice` string, required: Voice ID, e.g. 'alloy', 'AM:@narrator', or a provider voice ID
  - `response_format` string: Audio format: mp3, opus, aac, flac, wav, pcm. Default: mp3
  - `speed` number: Speed multiplier (0.25 to 4.0). Not all providers support speed control.

## Response `200`

Successful response

## Other responses

- `402`: Payment Required (x402 / MPP / np)

## Changes

- **2026-11-08** `857e915717f4`: 1 breaking
  - added required request body
- **2026-09-22** `f80c0aab1f7c`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/changes/allmodels/oai/audio/speech/post.md)

---

[API](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace.md) - [All operations](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/llms.txt) - [OpenAPI document](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/revisions/fc2e1d26c8eb?raw)