piper-plus Demo

High-quality text-to-speech synthesis supporting Japanese and English.

This demo uses ONNX models for fast CPU inference.

Select Model

Advanced Settings

0.5 2
0 1
0 1

Tips:

  • Japanese model expects hiragana/kanji text
  • English model works with standard text
  • Adjust speed for faster/slower speech
  • Higher expressiveness = more natural variation
Examples