Overview

This node integrates with the Wiro Kokoro TTS (Text-to-Speech) API to convert a given text prompt into natural-sounding audio. It allows users to specify the text prompt, select a voice from a wide range of options, and choose a language code for the speech output. The node sends the request to the Wiro API, waits for the audio generation task to complete by polling the task status, and then outputs the result including the task ID, status, and URL to the generated audio file if successful. This node is useful for automating audio content creation, such as generating voiceovers, announcements, or accessibility audio from text.

Use Case Examples

1. Generating an audio narration from a text script by selecting a preferred voice and language.
2. Creating automated voice messages for customer service or notifications using different voice profiles.
3. Converting written content into audio for podcasts or e-learning materials.

Properties

Output

JSON

• taskid - The unique identifier of the audio generation task.
• url - The URL to access the generated audio file once the task is completed.
• status - The status of the audio generation task, indicating if it is completed or failed.

Dependencies

• Wiro API key and secret credentials for authentication

Troubleshooting

• If the node throws an error indicating missing or invalid task ID or socket access token, verify that the Wiro API credentials are correct and that the API service is reachable.
• If the task status returns as failed, check the prompt text and parameters for validity and retry.
• Network issues or API rate limits may cause polling to fail; ensure stable internet connection and valid API usage limits.

Links

• Wiro Kokoro TTS API Documentation - Official documentation for the Wiro Kokoro Text-to-Speech API, including usage and parameters.