---
title: "Convert text to speech using a specified voice"
method: POST
path: "/v1/TextToSpeech"
---

# Convert text to speech using a specified voice

`POST /v1/TextToSpeech`

Synthesize speech from text with voice and gender customization, plus optional webhook callback.  
Give priority to the sample audio first, then to the voice ID, and lastly to gender.

## Request body

- union
  - object
    - `text` string, required — Text to convert to speech
    - `voice_id` string — Voice model ID
    - `gender` string — Gender preference for the voice (e.g., "male", "female")
    - `sample_audio_url` string, required — An audio URL containing a voice sample of the target speaker without music or overlapping voices. Recommended over voice_id for better output quality.
    - `webhook_url` string — Callback URL for async processing
  - object
    - `text` string, required — Text to convert to speech
    - `voice_id` string, required — Voice model ID
    - `gender` string — Gender preference for the voice (e.g., "male", "female")
    - `sample_audio_url` string — An audio URL containing a voice sample of the target speaker without music or overlapping voices. Recommended over voice_id for better output quality.
    - `webhook_url` string — Callback URL for async processing

## Response `200`

Successfully initiated TTS conversion

- object
  - `success` boolean
  - `task_id` string
  - `conversion_id` string
  - `eta` integer

## Other responses

- `402` — Payment Required
- `422` — Validation Error
- `500` — Server Error

---

[API](https://skmtc.net/musicgpt/apis/musicgpt-api.md) · [All operations](https://skmtc.net/musicgpt/apis/musicgpt-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/musicgpt/musicgpt-api/versions/6753dccf4c5d/schema)