Actions13
- Speech Actions
- Voice Actions
- History Actions
- User Actions
Overview
The "Generate Voice" operation of the Voice resource in this node allows users to create a synthetic voice sample based on specified speaker characteristics such as gender, accent, and age. It generates a temporary voice ID along with an audio sample that can be previewed. If the generated voice is satisfactory, users can then call a separate "Create Voice" operation using the generated voice ID to save or use the voice permanently.
This node is useful for applications involving text-to-speech synthesis where customized voices are needed, such as:
- Creating personalized voice assistants.
- Generating audio content with specific voice traits.
- Testing different voice styles before committing to a final voice creation.
Example: A user wants to generate a female British English voice of middle age reading a marketing script. They specify these parameters, get a sample audio, and if happy, proceed to create the voice for ongoing use.
Properties
| Name | Meaning |
|---|---|
| Gender Name or ID | The gender of the speaker. Choose from a predefined list or specify an ID via expression. Options are dynamically loaded. |
| Accent Name or ID | The accent of the speaker. Choose from a predefined list or specify an ID via expression. Options are dynamically loaded. |
| Age Name or ID | The age group of the speaker. Choose from a predefined list or specify an ID via expression. Options are dynamically loaded. |
| Additional Fields | A collection of optional fields: |
| - Binary Name | Change the output binary data name (default: "data"). |
| - File Name | Change the output file name for the generated audio (default: "voice"). |
| - Sample Text | The text string used to generate the voice sample. Defaults to a descriptive message about the node's functionality. |
| - Accent Strength | Numeric value controlling how strong the accent should be applied, ranging from 0.3 to 2, defaulting to 1. |
Note: The node includes notices informing users that it is in beta and under active development, with links for more information and support.
Output
The node outputs JSON data containing at least:
generated_voice_id: An identifier for the generated voice sample.- Audio sample data as binary output, representing the synthesized speech audio.
The binary output contains the audio file of the generated voice sample, which can be saved or played back directly within workflows.
Dependencies
- Requires an API key credential for authentication with the ElevenLabs API service.
- Network access to
https://api.elevenlabs.io/v1endpoint. - The node depends on dynamic loading of options for gender, accent, and age from the API or internal methods.
Troubleshooting
- Common issues:
- Invalid or missing API credentials will cause authentication failures.
- Specifying unsupported or incorrect IDs for gender, accent, or age may result in errors or no voice generation.
- Accent strength values outside the allowed range (0.3 to 2) might cause validation errors.
- Error messages:
- Authentication errors: Check that the API key credential is correctly configured.
- Validation errors on input properties: Ensure all required fields are filled and values are within allowed ranges.
- Network errors: Verify internet connectivity and API endpoint availability.