Last Update: 2025/3/26
LLMVision Voices API
The Voices feature provides functionalities for obtaining the voice list.
Endpoint
GET https://api.llmprovider.ai/api/voice
Request Headers
Header | Value |
---|---|
Content-Type | application/json |
Request Body
The request body should be a Query object with the following parameters:
Parameter | Type | Description | Note |
---|---|---|---|
page | int | The page number for pagination. | |
page_size | int | The number of items per page. | |
style | int64 | The style of the voice. | |
language | int64 | The language of the voice. | |
age | int64 | The age category of the voice. | |
emotion | int64 | The emotion expressed in the voice. | |
scope | int64 | The scope of the voice request. | |
gender | int64 | The gender of the voice. | |
keyword | string | The keyword for filtering voice requests. | |
status | int64 | The status of the voice request. |
Example Request
curl --location 'https://api.llmprovider.ai/api/voice?page=1&page_size=20'
Response
The API returns an audio file in the requested format.
{
"id": 6,
"voice_name": "奶声女童",
"description": "奶呼呼糯叽叽的幼童",
"scope": [
"角色扮演",
"聊天陪伴",
"有声读物"
],
"style": [
"可爱"
],
"language": [
"中文"
],
"age": [
"幼年"
],
"gender": "女声",
"emotion": [
"平稳"
],
"price": 1,
"avatar": "https://oss.llmprovider.ai/voice/avatar/08d566e7-bdf3-4130-b858-e3fd27004bba/f_c_0004.png",
"audio": [
"girl_naisheng"
],
"priority": 1,
"status": 2,
"voice_listen": [
{
"id": 7,
"name": "",
"use_label": "girl_naisheng",
"url": "https://oss.llmprovider.ai/voice/listen/57286b1e-6bfc-4622-b253-a4f12a0fe38f/tmpd67q4fc5.mp3",
"duration": 0,
"description": "我喜欢喝奶粉"
}
]
}
Note:
- fields such as language, style, and emotion may support multiple options.
- audio preview files can be directly accessed via the URL returned by voice_listen.
LLMVision Fusion Audio API
The Fusion Audio feature provides functionalities for facilitating future voice fusion.
Endpoint
GET https://api.llmprovider.ai/api/audio
Request Headers
Header | Value |
---|---|
Content-Type | application/json |
Request Body
The request body should be a Query object with the following parameters:
Parameter | Type | Description | Note |
---|---|---|---|
model_label | string | the voice model name |
Example Request
curl --location 'https://api.llmprovider.ai/api/audio?model_label=girl_naisheng'
Response
The API returns an audio file in the requested format.
For any questions or further assistance, please contact us at [email protected].