JigsawStack icon

JigsawStack

Use JigsawStack API

Actions20

Overview

This node integrates with the JigsawStack API to convert text into speech audio. It is designed for scenarios where users want to generate spoken audio from textual content, such as creating voiceovers, accessibility features, or automated announcements. For example, you can input a product description and get an audio file that reads it aloud, or convert chatbot responses into speech for voice assistants.

Properties

Name Meaning
Text The text string that will be converted into speech.
Accent The accent or voice code to use for speech synthesis (e.g., "en-US-female-7").
Custom Accent A custom accent code if the desired accent is not listed in the predefined options.
Speaker Clone URL A direct URL to an audio file used for cloning a specific voice style.
Return Type The format of the returned audio: Base64 encoded string, URL to the audio file, or binary data.
Voice ID Identifier for a specific cloned voice to use in synthesis.

Output

The node outputs a JSON object containing the generated speech audio in the requested format:

  • If Return Type is url, the output contains a URL pointing to the generated audio file.
  • If base64, the output includes the audio encoded as a Base64 string.
  • If binary, the audio is provided as binary data suitable for further processing or saving as a file.

This flexibility allows integration with various workflows depending on whether you want to store, stream, or directly use the audio data.

Dependencies

  • Requires an active API key credential for the JigsawStack service.
  • The node makes HTTP requests to the JigsawStack API endpoint at https://api.jigsawstack.com/v1.
  • Proper configuration of the API key in n8n credentials is necessary for authentication.

Troubleshooting

  • Invalid API Key or Authentication Errors: Ensure the API key credential is correctly set up and has the required permissions.
  • Unsupported Accent or Voice ID: Using an invalid or unsupported accent or voice ID may cause errors or fallback to default voices. Verify available accents and voice IDs with the service documentation.
  • Malformed Text Input: Empty or excessively long text inputs might cause failures; ensure the text property is properly populated and within any length limits imposed by the API.
  • Return Type Issues: Selecting binary output requires handling binary data downstream; improper handling may lead to corrupted files.
  • Network or API Downtime: Connectivity issues or API service interruptions will prevent successful execution.

Links and References

Discussion