---
title: "Generate Speech from Text"
method: POST
path: "/v1/audio/text-to-speech/{voice_id}"
tags: ["Audio"]
---

# Generate Speech from Text

`POST /v1/audio/text-to-speech/{voice_id}`

Generate speech from text using the specified voice and model.

This endpoint synchronously generates audio and returns the binary data directly.
The request will block until the TTS generation is complete.

## Path parameters

- `voice_id` string, required — Voice ID to use for TTS generation

## Headers

- `x-api-key` string, required — API Key for authentication

## Request body

- TTSRequest — Request body for text-to-speech generation
  - `text` string, required — The text to convert to speech
  - `model` 'mirage-audio-1', required — TTS model to use for generation

## Response `200`

Returns the generated audio file as binary data

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/mirage/apis/mirage-video-api.md) · [All operations](https://skmtc.net/mirage/apis/mirage-video-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/mirage/mirage-video-api/revisions/021b1eec81a4/schema)