> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax Voice Design

Generate a personalized custom voice from a text description. Returns a `voice_id` that can be used with the T2A speech synthesis API, as well as a hex-encoded preview audio sample.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="prompt" type="string" required={true}>
  Voice description text that defines the characteristics of the voice to generate.
</ParamField>

<ParamField body="voice_id" type="string">
  Custom voice ID. If not provided, the system will automatically create a unique voice\_id.
</ParamField>

<ParamField body="preview_text" type="string" required={true}>
  Text used to generate the preview audio sample, up to 500 characters.

  Length limit: 0 - 500
</ParamField>

## Response Information

<ResponseField name="voice_id" type="string" required={false}>
  Generated voice ID, which can be used with the T2A speech synthesis API.
</ResponseField>