Actions16
Overview
The "Generate Voice" operation in the Voice resource of 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. This is useful for applications like voice assistants, automated announcements, or any scenario where custom text-to-speech voices are needed. After generating a voice you like, you can use the generated voice ID to create a permanent voice profile with another operation.
Practical examples:
- Quickly preview different voice styles before committing to one.
- Generate audio samples for demos or presentations.
- Create personalized voice messages by specifying speaker attributes.
Properties
| Name | Meaning |
|---|---|
| Gender Name or ID | The gender of the speaker. Choose from a predefined list or specify an ID via expression. |
| Accent Name or ID | The accent of the speaker. Choose from a predefined list or specify an ID via expression. |
| Age Name or ID | The age group of the speaker. Choose from a predefined list or specify an ID via expression. |
| Additional Fields | A collection of optional fields: |
| - Binary Name | Change the output binary data property name (default: "data"). |
| - File Name | Change the output file name for the generated audio (default: "voice"). |
| - Sample Text | The text content used to generate the voice sample. Default text provided but can be customized. |
| - Accent Strength | Numeric value controlling how strong the accent should be, between 0.3 and 2 (default: 1). |
Output
The node outputs JSON data containing at least a generated_voice_id which identifies the created voice sample. Additionally, it returns an audio sample in binary form representing the generated voice speaking the sample text.
json: Contains metadata including the generated voice ID.binary: Contains the audio data of the generated voice sample, named according to the "Binary Name" property (default "data").
This allows downstream nodes to access both the voice identifier for further operations and the actual audio content for playback or storage.
Dependencies
- Requires an API key credential for authentication with the ElevenLabs API.
- Network access to
https://api.elevenlabs.io/v1. - The node uses internal methods to load options dynamically for gender, accent, and age selections.
Troubleshooting
- Common issues:
- Invalid or missing API key will cause authentication errors.
- Specifying invalid IDs for gender, accent, or age may result in API errors or no voice generation.
- Network connectivity problems can prevent the request from completing.
- Error messages:
- Authentication failures: Check that the API key credential is correctly configured.
- Validation errors: Ensure all required properties (gender, accent, age, accent strength) are set and valid.
- Rate limiting or quota exceeded: May require waiting or upgrading API plan.