TTS Bro icon

TTS Bro

Text-to-Speech using sherpa-onnx Kokoro model (pure WASM)

TTS Bro

AI-generated

Summary

Synthesize speech from text using the Kokoro TTS model, outputting audio as WAV or raw PCM binary data alongside metadata.

Inputs

  • main — The node processes each incoming item using the configured TTS parameters; input item content is not directly used for synthesis.

Output shape

array of output items, one per input item (or fewer if continueOnFail suppresses errors)

Each output item contains a JSON payload with synthesis metadata and a binary property with the generated audio data.

Examples

Example 1: Basic speech synthesis

Text: 'Hello world', Voice: '0 (AF - Default American Female)', Speed: 1, Format: 'wav'

Links

Discussion