MiniMax Voice Design

Input text content to design a voice and generate a custom voice.

POST /v1/voice_design

Request Headers

Parameter	Type	Required	Default	Description
Content-Type	string	Yes	application/json	Data exchange format
Authorization	string	Yes	-	Authentication info, format is Bearer <API_KEY>

Request Body

Parameter	Type	Required	Description
prompt	string	Yes	Voice description text
preview_text	string	Yes	Preview audio text, up to 500 characters. Synthesis fee is 2 yuan per 10,000 characters
voice_id	string	No	Custom generated voice ID; when not provided, the system automatically generates a unique ID
aigc_watermark	boolean	No	Whether to append an audio watermark beat marker at the end of the preview audio, default false

Request Example

curl --request POST \
  --url https://neolink.com/minimax/v1/voice_design \
  --header 'Authorization: Bearer <API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "讲述悬疑故事的播音员，声音低沉富有磁性，语速时快时慢，营造紧张神秘的氛围。",
    "preview_text": "夜深了，古屋里只有他一人。窗外传来若有若无的脚步声，他屏住呼吸，慢慢地，慢慢地，走向那扇吱呀作响的门……"
  }'

Successful Response (HTTP 200)

{
  "voice_id": "ttv-voice-2025060717322425-xxxxxxxx",
  "trial_audio": "hex 编码音频",
  "base_resp": {
    "status_code": 0,
    "status_msg": "success"
  }
}

Field	Type	Description
voice_id	string	The generated voice ID, used for subsequent speech synthesis
trial_audio	string	Preview audio in hex-encoded format
base_resp.status_code	int	Status code; see the error codes for specific definitions
base_resp.status_msg	string	Status details