# MiniMax Voice Design - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/api-reference/model-apis-minimax-voice-design

# MiniMax Voice Design

POST

/

v3

/

minimax-voice-design

MiniMax Voice Design

cURL

```
curl --request POST \
--url https://api.novita.ai/v3/minimax-voice-design \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"prompt": "<string>",
"voice_id": "<string>",
"preview_text": "<string>"
}
'
```

200

```
{
"voice_id": "<string>"
}
```

Generate personalized custom voices from text descriptions. Returns a voice_id for use in T2A speech synthesis APIs, along with a hex-encoded preview audio sample.

##

[​](#request-headers)

Request Headers

[​](#param-content-type)

Content-Type

string

required

Supports: `application/json`

[​](#param-authorization)

Authorization

string

required

Bearer authentication format, for example: Bearer {{API Key}}.

##

[​](#request-body)

Request Body

[​](#param-prompt)

prompt

string

required

Voice description text that defines the characteristics of the voice to generate.

[​](#param-voice-id)

voice_id

string

Custom voice ID for the generated voice. If not provided, a unique voice_id will be automatically created.

[​](#param-preview-text)

preview_text

string

required

Text used for generating a preview audio sample. Max 500 characters.Length limit: 0 - 500

##

[​](#response)

Response

[​](#param-voice-id-1)

voice_id

string

The generated voice ID, usable in T2A speech synthesis APIs.

Last modified on April 7, 2026