deAPI icon

deAPI

Generate images, videos, transcribe audio and boost prompts using deAPI AI models

Actions12

Audio → Clone a Voice

AI-generated

Summary

Clones a voice from a reference audio file and generates speech in that cloned voice.

Inputs

  • text (required) — The text to generate speech for.
  • lang (required) — Language for speech synthesis. Options: Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish.
  • refAudio (required) — The name of the binary field containing the reference audio file. Supported formats: MP3, WAV, FLAC, OGG, M4A. Max 10 MB. Duration must be between 3-10 seconds.
  • refText — Optional transcript of the reference audio for improved voice cloning accuracy.
  • format — Audio output format. Default: mp3. Options: FLAC, MP3, WAV.
  • waitTimeout — Maximum time to wait for completion in seconds. Default: 120. Range: 30-600.

Output shape

a single record (no body — success/failure only)

The operation returns the input item unchanged (pairedItem preserved). The node uses an asynchronous wait/resume pattern via webhook, meaning the actual audio generation happens in the background and is not returned by this node step.

Examples

Example 1: Clone a voice for a greeting message

Select 'Clone a Voice', set text to 'Welcome to our service', select language, provide a binary field for the reference voice, and optionally add a transcription for better accuracy.

Links

Discussion