Expressive Multilingual TTS

A multilingual expressive text-to-speech system available in two sizes:

The model supports mid-sentence language switching across many languages in a single utterance, e.g.:

Hi nama saya Husein, I am so cute, 我喜欢吃鸡饭, boire du thé glacé, ולהירגע על החוף, وأحب أن أتعرض لبعض أشعة الشمس.

Speaker
Model size
0.5 1.2

Note: Example texts are translated using Google Translate and may not be accurate — for demo purposes only.

Examples