Skip to main content
GET
Query MiniMax Preset Voice List

Authorizations

Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Query Parameters

language
enum<string>
default:zh

Language version of the returned data: zh (Chinese, default) / en (English). The voice_id is identical between the two versions; only the voice_name / language / accent / gender / age / tag_list / description text switches with the language.

Available options:
zh,
en
Example:

"zh"

Response

Query successful — returns an array of preset voices

id
string
required

Internal database ID of the voice (numeric string) — for internal traceability only; do not pass it to speech synthesis requests

Example:

"295"

voice_id
string
required

Voice ID. This is the value to pass directly into the voice_setting.voice_id field of speech synthesis requests.

Example:

"Arabic_CalmWoman"

voice_name
string
required

Display name of the voice (switches between Chinese / English based on language)

Example:

"Calm Woman"

language
string

Language the voice belongs to (switches between Chinese / English based on language, e.g. Arabic / 阿拉伯语, Chinese (Mandarin) / 中文-普通话)

Example:

"Arabic"

accent
string

Accent tag (switches between Chinese / English based on language, e.g. Standard / 标准口音). May be an empty string for some newer entries.

Example:

"Standard"

gender
string

Gender (switches between Chinese / English based on language, e.g. Male / Female / Character, or / / 角色)

Example:

"Female"

age
string

Age group (switches between Chinese / English based on language, e.g. Young / Middle-aged / Elderly / Child, or 青年 / 中年 / 老年 / 儿童). May be an empty string for some newer entries.

Example:

"Middle-aged"

tag_list
string[]

Style / scene tag list (switches between Chinese / English based on language). May be an empty array for some newer entries.

cover_url
string

Cover image URL. May be an empty string for some newer entries.

sample_audio
string

Sample audio URL (we recommend previewing it before selection)

description
string

Textual description of the voice (switches between Chinese / English based on language). May be an empty string for some newer entries.