Fish Audio List Voice Models API

List voice models with pagination. Filter by title, tags, author, language, and license status.

List voice models with pagination. Filter by title, tags, author, language, and license status, or return only models owned by the current workspace.

Synchronous endpoint: the request returns paginated results immediately. Use the model _id as reference_id on the Text to Speech endpoint.

Base URL

https://api.autorouter.top — Production

Authentication

BearerAuth: http (bearer) Authenticate using a Bearer Token. Format: Authorization: Bearer sk-xxxxxx

Endpoints

GET `/fishaudio/model`

List voice models

Return a model list using pagination and filters.

Headers

Name	Type	Required	Description
`Authorization`	string	Yes	Request authentication. Format: `Bearer sk-xxxxxx`

Query Parameters

Name	Type	Required	Description
`page_size`	integer	No	Page size. Default `10`, range `[1, 100]`
`page_number`	integer	No	Page number. Default `1`, minimum `1`
`title`	string \| null	No	Filter by title
`tag`	string \| string[] \| null	No	Filter by tag
`self`	boolean	No	If `true`, return only models owned by the current workspace. Default `false`
`author_id`	string \| null	No	Filter public models by author ID; ignored if `self=true`
`language`	string \| string[] \| null	No	Filter by language
`title_language`	string \| string[] \| null	No	Filter by title language
`licensed`	boolean	No	If `true`, only Fish Audio licensed voices are returned; ignored if `self=true`. Default `false`
`sort_by`	string	No	Sort field. Values: `score` (default), `task_count`, `created_at`

selfboolean(Optional)

Whether to return only models owned by the current workspace. Default false.

true: return only your models; author_id and licensed are ignored
false: follow public discovery rules; you can filter with author_id, licensed, and similar fields

sort_bystring(Optional)

Sort field. Default score.

score: overall score
task_count: usage count
created_at: created time

Responses

200: Retrieved successfully

Content-Type: application/json

401: Unauthorized

Content-Type: application/json

503: Service overloaded

Content-Type: application/json

Request Example

curl -X GET "https://api.autorouter.top/fishaudio/model?page_size=10&page_number=1&self=true&sort_by=created_at" \
  -H "Authorization: Bearer sk-xxxxxx"

Response Example

{
  "total": 1,
  "items": [
    {
      "_id": "7f8a9b0c1d2e3f4a5b6c7d8e",
      "type": "tts",
      "title": "My Voice",
      "description": "Cloned from a studio sample",
      "cover_image": "",
      "train_mode": "fast",
      "state": "trained",
      "tags": ["custom"],
      "samples": [],
      "created_at": "2026-09-20T01:00:00.000Z",
      "updated_at": "2026-09-20T01:00:00.000Z",
      "languages": ["en"],
      "visibility": "private",
      "lock_visibility": false,
      "default_text": "",
      "source": null,
      "licensed": false,
      "like_count": 0,
      "mark_count": 0,
      "shared_count": 0,
      "task_count": 0,
      "liked": false,
      "marked": false,
      "unliked": false,
      "author": {
        "_id": "64a1b2c3d4e5f67890123456",
        "nickname": "creator",
        "avatar": "https://example.com/avatar.png"
      }
    }
  ],
  "has_more": false,
  "total_is_exact": true,
  "window_limited": false,
  "max_offset": null,
  "accessible_upper_bound": null
}

Response fields:

Name	Type	Description
`total`	integer	Total number of matching models
`items`	object[]	Models on the current page
`has_more`	boolean \| null	Whether there is a next page
`total_is_exact`	boolean	Whether `total` is exact. Default `true`
`window_limited`	boolean	Whether the query window is limited. Default `false`
`max_offset`	integer \| null	Maximum offset
`accessible_upper_bound`	integer \| null	Accessible upper bound
`items[]._id`	string	Model ID, usable as TTS `reference_id`
`items[].type`	string	Model type. `tts` is text-to-speech; `svc` is singing voice conversion
`items[].title`	string	Model title
`items[].description`	string	Model description
`items[].cover_image`	string	Cover image URL
`items[].train_mode`	string	Training mode. `fast` or `full`
`items[].state`	string	State. Enum: `created`, `training`, `trained`, `failed`
`items[].tags`	string[]	Tag list
`items[].samples`	object[]	Preview samples
`items[].created_at`	string	Created at, ISO 8601
`items[].updated_at`	string	Updated at, ISO 8601
`items[].languages`	string[]	Language list
`items[].visibility`	string	Visibility. Enum: `public`, `unlist`, `private`
`items[].licensed`	boolean	Whether this is a Fish Audio licensed voice
`items[].like_count`	integer	Like count
`items[].task_count`	integer	Usage count
`items[].author`	object	Author information

itemsobject[](Required)

Models on the current page. Each item is a full model object.

_idstring(Required)

Model ID. After creation it can be used as TTS reference_id.

statestring(Required)

Model state. Enum: created, training, trained, failed. With train_mode=fast it usually becomes trained quickly.

authorobject(Required)

Author information, including _id, nickname, and avatar.

Error Handling

HTTP 401 / 403 Auth Errors

401 Unauthorized: API Key is invalid or expired
403 Forbidden: API Key cannot access this model (check the token model allowlist)

HTTP 402 Insufficient Balance

Returns insufficient user quota. Top up in the AutoRouter console.

HTTP 503 Service Overloaded

The server is too busy to process the request. Please retry later.

List Models

Base URL

Authentication

Endpoints

GET `/fishaudio/model`

Headers

Query Parameters

selfboolean(Optional)

sort_bystring(Optional)

Responses

Request Example

Response Example

itemsobject[](Required)

Error Handling

HTTP 401 / 403 Auth Errors

HTTP 402 Insufficient Balance

HTTP 503 Service Overloaded

On this page

List Models

selfboolean(Optional)

sort_bystring(Optional)

itemsobject[](Required)

Properties

On this page