Pass IndexThe State of AISign in

Fun-CosyVoice3-0.5B-2512

Fun-CosyVoice 3.0: Demos; Paper; Modelscope; Huggingface; CV3-Eval.

text → audio · made by QwenAudio

Sold by

Nobody in the catalogue publishes a price for this yet.

About

Fun-CosyVoice3-0.5B-2512 — an audio model from QwenAudio.

It takes text and returns audio. It was published in December 2025. The catalogue files it under speak. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
QwenAudio
Register
model
Takes
text
Returns
audio
Published
December 2025
Parameters
500 million · read from its own name
Licence
apache-2.0

Known as 1 name

FunAudioLLM/Fun-CosyVoice3-0.5B-2512