API DocsAI Model APIsAudioFish AudioModel Management

Get Model

Retrieve voice model details by model ID.

Retrieve voice model details by ID, including state, visibility, author, preview samples, and quality evaluation.

Synchronous endpoint: the request returns the model object immediately. Use _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/{id}

Get voice model details

Look up model details with the _id returned at creation. Returns 403 / 404 when access is denied or the model does not exist.

Headers

NameTypeRequiredDescription
AuthorizationstringYesRequest authentication. Format: Bearer sk-xxxxxx

Path Parameters

NameTypeRequiredDescription
idstringYesModel ID

Responses

200: Retrieved successfully

Content-Type: application/json

403: No permission to access this model

Content-Type: application/json

404: Model not found

Content-Type: application/json

Request Example

curl -X GET "https://api.autorouter.top/fishaudio/model/{id}" \
  -H "Authorization: Bearer sk-xxxxxx"

Response Example

{
  "_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"
  }
}

Response fields:

NameTypeDescription
_idstringModel ID, usable as TTS reference_id
typestringModel type. tts is text-to-speech; svc is singing voice conversion
titlestringModel title
descriptionstringModel description. Defaults to an empty string
cover_imagestringCover image URL. Defaults to empty
train_modestringTraining mode. fast is ready immediately after creation; full is full training
statestringState. Enum: created, training, trained, failed
tagsstring[]Tag list
samplesobject[]Preview samples. Defaults to an empty array
created_atstringCreated at, ISO 8601
updated_atstringUpdated at, ISO 8601
languagesstring[]Language list
visibilitystringVisibility. Enum: public, unlist, private
lock_visibilitybooleanWhether visibility is locked. Default false
dmca_taken_downboolean | nullWhether the model was taken down for DMCA
takedown_categorystring | nullTakedown category: dmca, policy
default_textstringDefault preview text
sourcestring | nullSource. May be voice_design when every uploaded voice verifies
licensedbooleanWhether this is a Fish Audio licensed voice
pvc_release_statestring | nullPVC release state: released, retiring
pvc_notice_period_monthsinteger | nullPVC notice period (months)
pvc_released_atstring | nullPVC released at
pvc_retire_requested_atstring | nullPVC retire requested at
pvc_retire_effective_atstring | nullPVC retire effective at
qualityobject | nullAudio quality evaluation
like_countintegerLike count
mark_countintegerMark count
shared_countintegerShare count
task_countintegerUsage count
likedbooleanWhether the current user liked it
markedbooleanWhether the current user marked it
unlikedbooleanWhether the current user unliked it
authorobjectAuthor information

statestring(Required)

Model state.

  • created: created
  • training: training
  • trained: complete and ready for TTS
  • failed: training failed

With train_mode=fast it usually becomes trained quickly.

authorobject(Required)

Author information.

_idstring(Required)

Author user ID.

nicknamestring(Required)

Author nickname.

avatarstring(Required)

Author avatar URL.

qualityobject | null(Optional)

Audio quality evaluation. null if not evaluated.

audiosobject[](Optional)

Quality details for each reference audio. Each item includes:

  • filename (string, required): file name
  • duration_ms (number, required): duration in milliseconds
  • language (string, optional): language, default unknown
  • quality (object, optional): quality score map
  • quality_passed (boolean, optional): whether quality checks passed, default false
  • quality_reason (string, optional): quality notes
created_atstring(Required)

Quality evaluation created at, ISO 8601.

updated_atstring(Required)

Quality evaluation updated at, ISO 8601.

Error Handling

HTTP 401 / 403 Auth Errors

  • 401 Unauthorized: API Key is invalid or expired
  • 403 Forbidden: no permission to access this model (private model or token lacks access)

HTTP 404 Model Not Found

The specified id does not exist. Confirm the model ID is correct and has not been deleted.

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

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

Update Model

Update the title, description, cover, visibility, or tags of an existing voice model.

On this page

Base URLAuthenticationEndpointsGET /fishaudio/model/{id}HeadersPath ParametersResponsesRequest ExampleResponse ExampleError HandlingHTTP 401 / 403 Auth ErrorsHTTP 404 Model Not FoundHTTP 402 Insufficient BalanceHTTP 503 Service Overloaded