Create Voice Profile

This endpoint can be used to create a new voice profile based on given audio inputs, and are useful for maintaining brand consistency and for reusing a character voice across various AI avatar videos.

To generate a new voice profile, send a POST request to /v1/voice-profiles helper endpoint with the body of the request containing the following parameters:

• voice_name: Name of the voice profile. This is a required field.
• reference_audio_urls: Array of one or more reference audio urls to be used as inputs for generation of voice profile. This is a required field.
• gender: An optional field to indicate the gender of the voice profile and the possible values include "male", "female" and "neutral".
• age: An optional field to indicate the age of the voice profile and the possible values are "child", "teen", "young-adult", "early-middle-aged", "late-middle-aged", and "senior".
• language: An optional field to indicate the primary language of the voice profile and the possible values are the codes of various languages. E.g., "en" for English, "es" for Spanish, etc.
• accent: An optional field to indicate the accent of the selected language. This field should be provided only if language field is being used. E.g., "en-american" for English US, "en-british" for English UK, etc. See API Docs to see all possible values for language and accent that are accepted.
• description: An optional description field for the voice.
• preview_text: An optional short sample script to demonstrate a voice's tone, pacing, and pitch. This will be used to generate the preview_url of the voice profile. It must be between 10 and 200 characters.

To learn more about the path parameters, request format, output format and schema information, please visit the detailed API docs of the Create Voice endpoint.