Wiro - Chatterbox Multilingual icon

Wiro - Chatterbox Multilingual

Generate expressive, natural speech in 23 languages. Features instant voice cloning from short

Wiro - Chatterbox Multilingual

AI-generated

Overview

This node integrates with the Wiro Chatterbox Multilingual API to generate expressive, natural speech in 23 different languages. It supports instant voice cloning from a short audio input and allows customization of speech characteristics such as expressiveness, randomness, and generation guidance. This node is useful for applications requiring multilingual text-to-speech synthesis with fine control over voice style and output quality, such as creating voiceovers, virtual assistants, or language learning tools.

Use Case Examples

  1. Generate a natural-sounding speech output in Spanish from a given text prompt with customized expressiveness and randomness settings.
  2. Clone a voice from a short audio clip and produce speech in Japanese with specific speech style parameters.
  3. Create multilingual voice responses for a chatbot by selecting the appropriate language and tuning speech parameters.

Properties

Name Meaning
Input Audio (Optional) URL URL of an audio file to use for instant voice cloning. Supported formats include .wav, .m4a, .mp3, .ogg, .opus, and webm.
Prompt Text prompt to generate speech from. This is a required input that guides the speech content.
Language Select the language for speech generation from 23 supported languages.
Exaggeration Controls speech expressiveness, ranging from 0.25 to 2.0, with 0.5 as neutral. Extreme values may cause instability.
Cfg Weight CFG/Pace weight controlling generation guidance, ranging from 0.2 to 1.0. Use 0.5 for balanced results and 0 for language transfer.
Temperature Controls randomness in generation, ranging from 0.05 to 5.0. Higher values produce more varied speech.
Top P Limits token selection to the most probable tokens that reach the cumulative probability p value, influencing speech variation.

Output

JSON

  • taskid - Identifier of the speech generation task.
  • url - URL to the generated speech audio file once the task is completed.
  • status - Status of the speech generation task, e.g., '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 correctly configured and that the API service is reachable.
  • If the speech generation task status is 'failed', check the input parameters for correctness, especially the audio URL format and prompt content.
  • Network issues or API rate limits may cause polling to fail; ensure stable internet connection and valid API usage limits.

Links

Discussion