ElevenLabs icon

ElevenLabs

Generate natural-sounding speech using ElevenLabs AI
Join our community

Actions13

Overview

The "Generate Voice" operation of the ElevenLabs node creates a new synthetic voice profile and returns a unique generated_voice_id along with an audio sample of that voice. This allows users to preview the generated voice before deciding to save it permanently by calling a separate "Create Voice" operation with the returned ID.

This node is useful in scenarios where you want to dynamically generate custom AI voices based on specific attributes such as gender, accent, and age, and then use those voices for text-to-speech applications, voice assistants, audiobooks, or any other project requiring natural-sounding speech synthesis.

Example use case:
You want to create a voice that sounds like a young female speaker with a British accent. You use this operation to generate a sample voice with those parameters, listen to the sample, and if satisfied, proceed to create and store the voice for future use.

Properties

Name Meaning
Gender Name or ID The gender of the speaker. Choose from a predefined list of genders or specify a custom ID using an expression.
Accent Name or ID The accent of the speaker. Choose from a predefined list of accents or specify a custom ID using an expression.
Age Name or ID The age group of the speaker. Choose from a predefined list of ages or specify a custom ID using an expression.
Additional Fields A collection of optional fields to customize the voice generation:
- Binary Name Change the name of the binary output data (default: "data").
- File Name Change the output file name for the generated audio (default: "voice").
- Sample Text The sample text used to generate the audio sample for the voice preview. Defaults to a descriptive sentence explaining the operation.
- Accent Strength A numeric value between 0.3 and 2 controlling how strong the accent should be applied to the voice. Default is 1.

Output

The node outputs JSON data containing at least the following:

  • generated_voice_id: A unique identifier for the newly generated voice profile.
  • An audio sample of the generated voice speaking the provided sample text.

If configured, the node also outputs the audio sample as binary data, which can be saved or played back directly within n8n workflows. The binary data represents the audio file of the voice sample.

Dependencies

  • Requires an API key credential from ElevenLabs, which must be configured in n8n prior to using the node.
  • The node communicates with the ElevenLabs API endpoint at https://api.elevenlabs.io/v1.
  • No additional external dependencies are required beyond the API key and internet access.

Troubleshooting

  • Common issues:

    • Missing or invalid API key: The node will fail to authenticate with the ElevenLabs API. Ensure your API key is correctly set up in n8n credentials.
    • Invalid property values: Providing unsupported gender, accent, or age IDs may cause errors. Use the provided dropdown options or valid expressions.
    • Accent strength out of range: Values must be between 0.3 and 2; otherwise, the request may be rejected.

  • Error messages:

    • Authentication errors typically indicate problems with the API key.
    • Validation errors often point to incorrect or missing required properties.
    • Network or API downtime errors require checking internet connectivity or ElevenLabs service status.

Links and References

Discussion