Skip to main content

Clone Voice

Creates a clone of a voice using audio samples. This creates a new voice that mimics the characteristics of the provided audio.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.

Inputs​

  • Connection Id (String) - Connection ID from the Connect node. Optional if you provide API Key directly.
  • Voice Name (String) - Name for the cloned voice.
  • Audio Files (Array) - Array of audio file paths containing speech to clone. Multiple samples create better clones.

Options​

  • Description (String) - Optional description for the cloned voice.
  • API Key - Your ElevenLabs AI API key. Optional if using Connection ID.

Outputs​

  • Cloned Voice (Object) - Information about the newly cloned voice including:
    • voice_id - Unique identifier for the cloned voice
    • name - Voice name
    • category - Voice category
    • Other voice metadata

How It Works​

The Clone Voice node creates a voice clone from audio samples. When executed, the node:

  1. Validates that voice name and audio files are provided
  2. Either uses the provided connection or creates a new client with direct API key
  3. Opens each audio file for processing
  4. Calls the ElevenLabs voice cloning API
  5. Closes all file handles
  6. Returns the cloned voice information with its unique voice_id

Requirements​

  • Valid ElevenLabs API key (via Connect node or direct option)
  • Voice name
  • At least one audio file (multiple recommended for better cloning)
  • Audio files must exist and be accessible
  • High-quality, clear audio for best results

Error Handling​

The node will return specific errors in the following cases:

  • Missing voice name - "Voice Name cannot be empty. Please provide a name for the cloned voice."
  • Missing audio files - "Audio Files cannot be empty. Please provide at least one audio file for voice cloning."
  • File not found - "Audio file not found. Please verify the file path is correct: [error details]"
  • Cloning failure - "Failed to clone voice: [error details]"

Usage Notes​

  • Audio Requirements for best cloning results:
    • Clear, high-quality recordings
    • Minimal background noise
    • Natural, conversational speech
    • Varied emotional tones and pitch ranges
    • 1-3 minutes total across all samples recommended
    • Consistent audio format and quality across samples
  • Multiple Samples - Using 2-5 audio samples typically produces better clones than a single file
  • Voice cloning captures the unique characteristics of the speaker
  • The cloned voice can be used immediately in Text to Speech and Speech to Speech nodes
  • Save the returned voice_id for future use
  • Cloned voices count toward your ElevenLabs account limits
  • Ensure you have permission to clone the voice you're using

Example Use Cases​

  • Creating a digital version of your own voice for automation
  • Cloning a voice actor's performance for consistent narration
  • Preserving a family member's voice
  • Building character voices for games or applications
  • Creating voice doubles for content creators
  • Generating consistent brand voices across materials
  • Cloning historical recordings for preservation
  • Building multilingual versions of a speaker's voice