Skip to main content

Add Voice

Creates a new custom voice in ElevenLabs using audio samples. This allows you to generate a unique voice from provided audio files.

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.
  • Name (String) - Name for the new voice.
  • Files (Array) - Array of audio file paths to use for creating the voice. Provide multiple samples for better quality.

Options​

  • Description (String) - Optional description for the voice to help identify its characteristics or use case.
  • Labels (String) - Optional JSON string containing labels for the voice (e.g., {"accent": "American", "age": "middle aged", "gender": "female"}).
  • API Key - Your ElevenLabs AI API key. Optional if using Connection ID.

Outputs​

  • Voice (Object) - Created voice information including:
    • voice_id - Unique identifier for the new voice
    • name - Voice name
    • category - Voice category
    • Other voice metadata

How It Works​

The Add Voice node creates a custom voice from audio samples. When executed, the node:

  1. Validates that name and audio files are provided
  2. Parses labels if provided (must be valid JSON)
  3. Either uses the provided connection or creates a new client with direct API key
  4. Prepares the audio file paths
  5. Calls the ElevenLabs API to create the voice with all parameters
  6. Returns the created voice information including its unique voice_id

Requirements​

  • Valid ElevenLabs API key (via Connect node or direct option)
  • Voice name
  • At least one audio file (multiple samples recommended for better quality)
  • Labels must be valid JSON if provided
  • Audio files should be clear, high-quality recordings

Error Handling​

The node will return specific errors in the following cases:

  • Missing name - "Name cannot be empty. Please provide a name for the new voice."
  • Missing files - "Files cannot be empty. Please provide at least one audio file for voice creation."
  • Invalid labels - "Labels must be a valid JSON string (e.g., {"accent": "American"})."
  • Creation failure - "Failed to add voice: [error details]"

Usage Notes​

  • Audio Quality - Use high-quality, clear audio samples for best results:
    • Minimal background noise
    • Consistent volume levels
    • Clear speech without distortion
    • Sample length: 1-3 minutes of audio recommended
  • Multiple Samples - Providing multiple audio samples improves voice quality and consistency
  • Labels - Use labels to categorize and find voices easily:
    • accent: "American", "British", "Australian", etc.
    • age: "young", "middle aged", "old"
    • gender: "male", "female", "neutral"
    • use_case: "narration", "conversational", "characters"
  • The created voice can be used immediately in Text to Speech and other nodes
  • Save the returned voice_id for future use
  • Custom voices count toward your ElevenLabs account limits

Example Use Cases​

  • Creating a custom brand voice from company spokesperson recordings
  • Generating character voices for storytelling or gaming
  • Building a voice library from different speakers
  • Creating voices that match specific accents or speaking styles
  • Preserving someone's voice for future use
  • Building personalized voice assistants