List Available Voices

This documentation provides comprehensive details about the voices available for synthesizing speech using our Text-to-Speech (TTS) service.

Endpoint Details

• URL: {{Address}}/v1/speech/synthesis/voices
• HTTP Method: GET
• HTTP Request: GET v1/speech/synthesis/voices
• Summary: Returns information about available voices for speech synthesis.
• Request: No arguments required.

Query Parameters (Optional)

You have the option to filter available voices based on culture and gender using query parameters. For example, you can query voices by language and gender as follows:

• /{{Address}}v1/speech/synthesis/voices/?language=tr-TR&gender=female

Response

The response provides information about available voices in JSON format.

Success Response Example

{
  "voices": [
    {
      "gender": "Male",
      "name": "GVZ Craig 8k",
      "language": "en-US"
    },
    {
      "gender": "Female",
      "name": "GVZ Gul 8k_HV_Premium",
      "language": "tr-TR"
    }
  ],
  "count": 2,
  "success": true,
  "errorMessage": null,
  "errorCode": null,
  "moreInfo": null
}

Response Fields Descriptions

Response:

• Voices: An array of Voice objects providing information about all available voices.
• Count: The number of available voices.
• Success: true if the request succeeded; false if it failed.
• ErrorMessage: In case of a failed request, this field contains the error message.
• ErrorCode: In case of a failed request, this field contains the error code (e.g., Internal Server Error).
• MoreInfo: Additional information about the response.

Voice Object (Voices):

• Gender: The gender of the voice (e.g., Male, Female, Neutral).
• Name: The name of the voice, used as the voice identifier in requests for text-to-speech (TTS) operations.
• Language: The language and region of the voice (e.g., en-US for US English).