Skip to content
KugelAudioDocs

Models API

REST reference for GET /v1/models: list the text-to-speech model IDs your KugelAudio requests can use, and the fields of each returned model object.

List Models

Get the TTS model IDs accepted for generation. This catalog is public and is filtered to models whose engine deployment is currently wired.

GET/v1/models
curl -X GET "https://api.kugelaudio.com/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"
{
  "models": [
    {
      "id": "kugel-3",
      "model_id": "kugel-3",
      "name": "Kugel 3",
      "description": "Most Natural",
      "parameters": null,
      "max_input_length": 10000,
      "sample_rate": 24000
    },
    {
      "id": "kugel-3.5",
      "model_id": "kugel-3.5",
      "name": "Kugel 3.5",
      "description": "Most Natural",
      "parameters": null,
      "max_input_length": 10000,
      "sample_rate": 24000
    }
  ]
}

Response


Model Object

Fields

The top-level response field models is an array of the model objects below.

FieldTypeDescription
idstringModel identifier accepted in API calls
model_idstringSame as id (backward compat)
namestringHuman-readable name
descriptionstring | nullModel description
parametersstring | nullnull for current models
max_input_lengthintegerMaximum input text length in characters
sample_rateintegerNative model sample rate in Hz; generation endpoints can resample output

For what each model is for, its input limit, and legacy IDs, see Models. Concurrency limits are plan-dependent; see pricing.