KittenTTS is an open source text-to-speech (TTS) model developed by the KittenML team and designed with a focus on lightweight and efficiency. Its distinguishing feature is that the model is less than 25MB in size, contains only about 15 million parameters, and can be run on low-end devices through the CPU alone without GPU support. This makes KittenTTS particularly well suited for embedded devices, edge computing and offline scenarios. KittenTTS delivers high-quality speech generation performance while maintaining an extremely small footprint compared to other leading TTS models on the market.
This answer comes from the articleKittenTTS: Lightweight Text-to-Speech ModelingThe
May not be reproduced without permission:AI productivity tools " KittenTTS is a lightweight text-to-speech model
English 
简体中文 
日本語 
Deutsch 
Português do Brasil