Skip to main content

Get Voices

Retrieves all available voices from your ElevenLabs AI account, including both pre-made and custom voices.

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.

Options​

  • API Key - Your ElevenLabs AI API key. Optional if using Connection ID.

Outputs​

  • Voices (Object) - List of all available voices with their details, including:
    • voice_id - Unique identifier for each voice
    • name - Display name of the voice
    • category - Voice category (e.g., premade, cloned, generated)
    • description - Voice description
    • labels - Voice characteristics and metadata
    • preview_url - URL to preview audio sample
    • settings - Voice generation settings

How It Works​

The Get Voices node retrieves your voice library. When executed, the node:

  1. Either uses the provided connection or creates a new client with direct API key
  2. Calls the ElevenLabs API to retrieve all voices
  3. Returns the complete list of voices with their metadata

Requirements​

  • Valid ElevenLabs API key (via Connect node or direct option)

Error Handling​

The node will return an error in the following case:

  • Retrieval failure - "Failed to retrieve voices: [error details]"

Usage Notes​

  • Returns both ElevenLabs pre-made voices and your custom voices
  • Use the voice_id from the output in Text to Speech, Speech to Speech, or other voice-related nodes
  • The voices list includes professional voices and any voices you've cloned or created
  • Voice metadata helps you select the right voice for your use case
  • Labels can indicate voice characteristics like age, gender, accent, use case, etc.
  • Preview URLs allow you to listen to voice samples before using them
  • This is useful for dynamically selecting voices based on requirements

Example Use Cases​

  • Listing all available voices for user selection
  • Finding voices with specific characteristics or accents
  • Auditing your voice library
  • Building voice selection interfaces
  • Checking which voices are available before generating speech
  • Retrieving voice IDs programmatically for automation workflows