Models Endpoint

This endpoint provides information about available TTS models from supported providers.

Request

GET /v1/models

Query Parameters

Parameter	Type	Required	Description
provider	string	No	Filter models by provider (e.g., aws, google, azure).

Example Request

curl -X GET "https://api.uberduck.ai/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

Response Body

Field	Type	Description
models	array	Array of model objects.
total	integer	Total number of models.

Model Object

Field	Type	Description
id	string	Unique identifier for the model.
name	string	Display name of the model.
provider_id	string	Identifier for the model provider.
provider_name	string	Display name of the model provider.
description	string	Description of the model.
features	array	Array of features supported by the model.
is_default	boolean	Whether this is the default model for the provider.

Example Response

{
  "models": [
    {
      "id": "polly_standard",
      "name": "Standard",
      "provider_id": "aws",
      "provider_name": "Amazon Polly",
      "description": "Amazon Polly's standard text-to-speech voices using concatenative synthesis",
      "features": ["fast-synthesis", "low-latency"],
      "is_default": true
    },
    {
      "id": "polly_neural",
      "name": "Neural",
      "provider_id": "aws",
      "provider_name": "Amazon Polly",
      "description": "Amazon Polly's neural text-to-speech voices using deep learning",
      "features": ["natural-sounding", "expressiveness", "high-quality"],
      "is_default": false
    },
    {
      "id": "google_standard",
      "name": "Standard",
      "provider_id": "google",
      "provider_name": "Google Cloud",
      "description": "Google's standard TTS voices",
      "features": ["fast-synthesis", "wide-language-support"],
      "is_default": true
    },
    {
      "id": "google_wavenet",
      "name": "WaveNet",
      "provider_id": "google",
      "provider_name": "Google Cloud",
      "description": "Google's WaveNet voices for more natural sounding speech",
      "features": ["natural-sounding", "high-quality", "expressiveness"],
      "is_default": false
    },
    {
      "id": "google_neural2",
      "name": "Neural2",
      "provider_id": "google",
      "provider_name": "Google Cloud",
      "description": "Google's Neural2 voices with enhanced naturalness and quality",
      "features": ["natural-sounding", "high-quality", "latest-technology"],
      "is_default": false
    },
    {
      "id": "azure_neural",
      "name": "Neural",
      "provider_id": "azure",
      "provider_name": "Microsoft Azure",
      "description": "Microsoft's neural voices for human-like, natural speech",
      "features": ["human-like", "prosody", "high-quality"],
      "is_default": true
    }
  ],
  "total": 6
}

Error Codes

Status Code	Error Code	Description
400	invalid_request	Invalid request parameters.
401	unauthorized	Invalid or missing API key.
429	rate_limit_exceeded	Rate limit exceeded.
500	internal_error	Internal server error.

Available Model Features

Models may include one or more of the following features:

Feature	Description
fast-synthesis	Quick audio generation with lower latency.
low-latency	Optimized for real-time or near-real-time applications.
natural-sounding	More human-like speech quality.
expressiveness	Better emotional range and expressivity.
high-quality	Higher audio fidelity and clarity.
wide-language-support	Supports multiple languages.
human-like	Very close to human speech patterns and quality.
prosody	Advanced control over intonation, stress, and rhythm.
latest-technology	Uses the newest speech synthesis technologies.

Usage Notes

• The models endpoint is useful for discovering available models and their capabilities.
• When using the text-to-speech endpoint, you'll need to specify a model ID from this list.
• Each model is compatible with specific voices. Check the voice details to confirm compatibility.
• Provider-specific features and parameters are available for each model. See the text-to-speech endpoint documentation for details.