Actions13
- Speech Actions
- Voice Actions
- History Actions
- User Actions
Overview
The Generate Voice operation in the "Voice" resource of this custom n8n node allows you to generate a synthetic voice sample based on selected characteristics such as gender, accent, and age. It returns a generated_voice_id along with an audio sample. This is useful for prototyping or previewing voices before creating a permanent voice profile.
Common scenarios:
- Generating sample voices for text-to-speech applications.
- Previewing different voice configurations (gender, accent, age) before committing to a specific voice.
- Automating voice generation for content creation, accessibility tools, or virtual assistants.
Practical example:
A user wants to create a demo of their app using a British female voice aged 30. They use this node to generate a sample, listen to it, and if satisfied, proceed to create the full voice profile.
Properties
| Display Name | Type | Description |
|---|---|---|
| Gender Name or ID | options | The gender of the speaker. Choose from a list or specify an ID via expression. |
| Accent Name or ID | options | The accent of the speaker. Choose from a list or specify an ID via expression. |
| Age Name or ID | options | The age of the speaker. Choose from a list or specify an ID via expression. |
| Additional Fields | collection | Optional fields to further customize the output: |
| - Binary Name | string | Change the output binary property name (default: data). |
| - File Name | string | Change the output file name (default: voice). |
| - Sample Text | string | The sample text used for generating the voice. |
| - Accent Strength | number | Required. Controls how strong the accent is (range: 0.3–2, default: 1). |
Note: Some properties are marked as required and must be provided for successful execution.
Output
- json:
- Contains at least a
generated_voice_id(string) identifying the generated voice. - May include additional metadata about the generated voice.
- Contains at least a
- binary:
- An audio sample of the generated voice, typically in a standard audio format (e.g., MP3 or WAV).
- The binary property name and file name can be customized via input properties.
Dependencies
- External Service: Requires access to the ElevenLabs API.
- API Key: You must configure valid ElevenLabs API credentials in n8n (
elevenLabsApi). - Environment: No special environment variables beyond n8n credential configuration.
Troubleshooting
Common issues:
Missing or invalid credentials:
Error: "No credentials found" or authentication errors.
Resolution: Ensure that the ElevenLabs API credentials are correctly set up in n8n.Required fields missing:
Error: "Missing required parameter: gender/accent/age."
Resolution: Make sure all required fields (Gender, Accent, Age) are filled.Invalid option values:
Error: "Invalid value for gender/accent/age."
Resolution: Use the provided options or ensure your custom IDs are correct.API limits or quota exceeded:
Error: "Rate limit exceeded" or similar messages from the ElevenLabs API.
Resolution: Check your ElevenLabs account limits.