Retrieve the list of system and cloned audio voices
December 23, 2024 (January 12, 2024)
Table of contents
Please configure at least one www.hailuo.ai account for this endpoint, see Setup MiniMax for details.
Over 300 pre-built voices provided supporting the following:
- Languages: English, Chinese (Mandarin), Spanish, French, Russian, Portuguese, Indonesian, German, Japanese, Korean, Italian, Cantonese
- Emotions: happy, sad, angry, fearful, disgusted, surprised, neutral
- Accents: US (General), English, Indian
- Ages: Young Adult, Adult, Middle-Aged, Senior
- Genders: Male, Female
https://api.useapi.net/v1/minimax/audio/voices/?…
Request Headers
Authorization: Bearer {API token}
Content-Type: application/json
API token
is required, see Setup useapi.net for details.
Query Parameters
-
account
is optional when only onewww.hailuo.ai
account configured. However, if you have multiple accounts configured, this parameter becomes required. -
tag_list
is optional. Specify a comma-separated list of tags using those returned by GET audio/config to narrow down the returned results.
Example:Italian,Female,Adult,Calm
-
page
andpage_size
are optional. Use them to retrieve the next page of data when the returnedhas_more
field istrue
.
Defaultpage_size
is 500. -
is_system
is optional. Set tofalse
if you want to retrieve a list of custom voices cloned via POST audio/clone-voice. The entire list of custom voices will be returned at once, thepage
andpage_size
parameters will not be used.
Default istrue
(return system voices).
Responses
-
GET
https://api.useapi.net/v1/minimax/audio/voices/?tag_list=Italian,Female,Adult,Calm{ "voice_list": [ { "voice_id": "209544421245048", "parent_voice_id": "0", "voice_name": "Diligent Leader", "tag_list": [ "Italian", "Female", "Adult", "Calm", "Standard" ], "file_id": "", "cover_url": "https://cdn.hailuoai.video/moss/staging/2024-11-21-14/moss-audio/voice_cover//1732171514479796864-207331589841022.png?x-oss-process=image/resize,p_50/format,webp", "create_time": 1732711650948, "update_time": 1732711650948, "collected": false, "voice_status": 2, "sample_audio": "https://cdn.hailuoai.video/moss/staging/2024-11-25-20/moss-audio/voice_sample_audio/1732537441602153587-official_sample_audio/4_it05.mp3", "uniq_id": "Italian_DiligentLeader", "group_id": "0" } ], "total": 1, "has_more": false }
-
{ "error": "<Error message>", "code": 400 }
-
{ "error": "Unauthorized", "code": 401 }
Model
{ // TypeScript, all fields are optional
voice_list: {
voice_id: string
parent_voice_id: string
voice_name: string
tag_list: string[]
file_id: string
cover_url: string
create_time: number
update_time: number
collected: boolean
voice_status: number
sample_audio: string
uniq_id: string
group_id: string
managed_by_api: boolean
is_expired: boolean
refresh_count: number
cloned_id: string
clone: {
voice_name: string
language_tag: string
need_noise_reduction: boolean
files: {
file_id: string
file_name: string
}[]
}
}[]
total: number
has_more: boolean
}
Examples
-
curl "https://api.useapi.net/v1/minimax/audio/voices/?account=account" \ -H "Accept: application/json" \ -H "Authorization: Bearer …"
-
const token = "API token"; const account = "Previously configured account"; const apiUrl = `https://api.useapi.net/v1/minimax/audio/voices/?account=${account}`; const response = await fetch(apiUrl, { headers: { "Authorization": `Bearer ${token}`, }, }); const result = await response.json(); console.log("response", {response, result});
-
import requests token = "API token" account = "Previously configured account" apiUrl = f"https://api.useapi.net/v1/minimax/audio/voices/?account={account}" headers = { "Content-Type": "application/json", "Authorization" : f"Bearer {token}" } response = requests.get(apiUrl, headers=headers) print(response, response.json())