Async icon

Async

Interact with Async API

Actions4

Voice → Create Clone

AI-generated

Summary

Creates a new custom voice clone using uploaded audio files and metadata.

Inputs

  • name — The name for the cloned voice.
  • audioFiles (required) — The audio files (binary data) used to train the voice clone.
  • additionalFields.accent — An accent identifier for the voice (e.g. American (US)).
  • additionalFields.description — A description of the cloned voice (e.g. Calm, neutral-tone female voice).
  • additionalFields.enhance — Whether to enhance (remove background noise of) the audio clip before cloning.
  • additionalFields.gender — The gender of the voice (Male, Female, or Neutral).
  • additionalFields.style — Comma-separated voice style(s).
  • requestOptions — Options for batching, SSL, proxy, and timeout.

Output shape

One item per input item, containing the response headers and the voice ID in the JSON node data.

The node processes input items individually to create a clone. The response is returned as JSON with the voice ID, along with the server's response headers.

Examples

Example 1: Create a named clone from a single audio file

Name: 'My Voice', Audio Files: [binary data from previous node], Additional Fields: Gender 'Female'

Links

Discussion