Wiro - Gemini 2.5 TTS icon

Wiro - Gemini 2.5 TTS

Google's Gemini 2.5 Flash Text To Speech Preview model

Wiro - Gemini 2.5 TTS

AI-generated

Overview

This node integrates with Google's Gemini 2.5 Flash Text To Speech (TTS) model via the Wiro API. It converts a given text prompt into speech audio using a selected voice from a predefined list. This node is useful for automating voice generation tasks such as creating audio content, voiceovers, or accessibility features in workflows.

Use Case Examples

  1. Convert a text prompt into speech audio using a female voice named 'Achernar'.
  2. Generate male voice audio from a given prompt using the 'Charon' voice option.

Properties

Name Meaning
Prompt The text input that will be converted into speech audio.
Voice The selected voice option to use for speech synthesis, with multiple male and female voice choices available.

Output

JSON

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

Dependencies

  • Wiro API key and secret credentials for authentication

Troubleshooting

  • If the node throws an error stating 'Wiro API did not return a valid task ID or socket access token', it indicates an issue with the API response. Verify the API credentials and network connectivity.
  • Task status codes '-1', '-2', '-3', or '-4' indicate failure states. Check the prompt input and voice selection for validity and retry.
  • Ensure the Wiro API credentials (API key and secret) are correctly configured in the node settings to avoid authentication errors.

Links

Discussion