Voices Endpoint

This endpoint provides access to the available voices in the Uberduck API. You can retrieve a list of all voices or filter them by various attributes.

Request

GET /v1/voices

Query Parameters

Parameter	Type	Required	Description
age	string	No	Filter by voice age (e.g., child, young, middle_aged, old).
gender	string	No	Filter by voice gender (e.g., male, female).
accent	string	No	Filter by voice accent (e.g., american, british, australian).
mood	string	No	Filter by voice mood (e.g., happy, sad, angry).
style	string	No	Filter by voice style (e.g., casual, formal, newsreader).
language	string	No	Filter by voice language (e.g., english, spanish, french).
limit	integer	No	Maximum number of voices to return. Default: 100. Maximum: 1000.
offset	integer	No	Number of voices to skip. Used for pagination. Default: 0.
name	string	No	Filter by voice name.
uuid	string	No	Filter by voice UUID.
model	string	No	Filter by model ID (e.g., polly_neural, google_wavenet, azure_neural).
search_term	string	No	Search term to match against voice name or display name.
tag	string	No	Filter by voice tag (e.g., characters, celebrities, accents).

Model-Specific Filtering

For model filtering, you can use these special formats:

• polly_neural - Returns Polly voices that support the neural engine
• polly_standard - Returns Polly voices that support the standard engine
• google_wavenet - Returns Google WaveNet voices
• google_neural2 - Returns Google Neural2 voices
• google_standard - Returns Google standard voices
• azure_neural - Returns Azure neural voices

Example Request

curl -X GET "https://api.uberduck.ai/v1/voices?language=english&gender=female&limit=10" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

Response Body

Field	Type	Description
voices	array	Array of voice objects.
total	integer	Total number of voices matching the filter criteria.

Voice Object

Field	Type	Description
voicemodel_uuid	string	Unique identifier for the voice.
display_name	string	Display name of the voice.
description	string	Description of the voice.
is_private	boolean	Whether the voice is private.
age	string	Age category of the voice.
gender	string	Gender of the voice.
accent	string	Accent of the voice.
style	string	Style of the voice.
mood	string	Mood of the voice.
image_url	string	URL to an image representing the voice.
sample_url	string	URL to a sample audio of the voice.
name	string	Internal name of the voice.
language	string	Language of the voice.
tags	array	Array of tags associated with the voice.
features	array	Array of features supported by the voice.

Example Response

{
  "voices": [
    {
      "voicemodel_uuid": "polly_joanna",
      "display_name": "Joanna",
      "description": "Professional female voice with an American accent",
      "is_private": false,
      "age": "middle_aged",
      "gender": "female",
      "accent": "american",
      "style": "professional",
      "mood": "neutral",
      "image_url": "https://static.uberduck.ai/voices/polly_joanna.png",
      "sample_url": "https://static.uberduck.ai/voices/samples/polly_joanna.mp3",
      "name": "polly_joanna",
      "language": "english",
      "tags": ["professional", "clear", "friendly"],
      "features": ["ssml", "neural-quality"]
    }
    // More voice objects...
  ],
  "total": 150
}

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.

Usage Notes

• Use pagination parameters (limit and offset) to navigate through large result sets.
• Combine multiple filter parameters to narrow down the results.
• The search_term parameter performs a partial match search on both the name and display_name fields.
• For provider voices, the voicemodel_uuid includes the provider prefix (e.g., polly_joanna, google_wavenet_a).
• The tags field is useful for finding voices with specific characteristics.