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

# Create speech

`POST /v1/audio/speech`

Convert text into speech audio and stream the generated bytes.

## Request body

- SpeechModel
  - `model` string, required — Text-to-speech model identifier.
  - `input` string, required — Text to synthesize into speech audio.
  - `voice` string, required — Voice preset to synthesize with.
  - `speed` number — Optional playback speed multiplier.
  - `instructions` string
  - `response_format` 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm', nullable

## Response `200`

Generated audio stream.

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `402` — Insufficient credits
- `403` — Forbidden
- `410` — Model deprecated
- `422` — Validation error
- `429` — Rate limited
- `500` — Internal server error
- `503` — Upstream service error

---

[API](https://skmtc.net/naga/apis/nagaai-api.md) · [All operations](https://skmtc.net/naga/apis/nagaai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/naga/nagaai-api/revisions/8bfb4677a79e/schema)