Skip to main content
GET
/
v1
/
voices
List Voices
curl --request GET \
  --url https://api.voxnexus.ai/v1/voices \
  --header 'X-Api-Key: <api-key>'
{
  "voices": [
    {
      "voice_id": "vl-xiaoxiao",
      "name": "Xiaoxiao",
      "gender": "female",
      "primary_locale": "zh-CN",
      "display_name": "Xiaoxiao",
      "category": "premade",
      "description": "A warm and friendly female voice, suitable for general scenarios",
      "is_multilingual": true,
      "supported_locales": [
        {
          "locale": "zh-CN",
          "language": "zh",
          "locale_name": "Chinese (Simplified, China)",
          "accent": "mandarin",
          "preview_url": "https://api.voxnexus.ai/samples/vl-xiaoxiao/zh-CN.mp3",
          "is_primary": true
        }
      ],
      "labels": {
        "personalities": [
          "warm",
          "friendly"
        ],
        "scenarios": [
          "assistant",
          "news"
        ]
      },
      "preview_url": "https://api.voxnexus.ai/samples/vl-xiaoxiao.mp3",
      "config_schema": {},
      "models": [
        "vn-tts-basic",
        "vn-tts-ultra"
      ]
    }
  ],
  "pagination": {
    "page": 1,
    "page_size": 20,
    "total": 150,
    "total_pages": 8
  }
}

Authorizations

​
X-Api-Key
string
header
required

Authenticate using X-Api-Key header

Query Parameters

​
language
string

Language code (optional)

Example:

"zh"

​
locale
string

Locale code (optional, e.g., zh-CN, en-US)

Example:

"zh-CN"

​
gender
enum<string>

Gender (optional)

Available options:
male,
female,
neutral
​
category
enum<string>

Voice category (optional)

Available options:
premade,
cloned,
generated
​
model_id
string

Model identifier (optional). Filters voices by the specified model's providers. Only voices belonging to providers configured for this model will be returned.

Example:

"vn-tts-ultra"

​
style
string

Voice style filter (optional). Filters voices that support the specified style in their config_schema.style.enum. Common styles: cheerful, sad, angry, friendly, newscast, etc.

Example:

"cheerful"

​
page
integer
default:1

Page number (default 1)

Required range: x >= 1
​
page_size
integer
default:20

Items per page (default 20, max 100)

Required range: 1 <= x <= 100

Response

Successfully returns voice list

​
voices
object[]
required

Voice list

​
pagination
object
required