Pass IndexThe State of AISign in

Confucius4-R2T2

Confucius4-R2T2 is a low-latency and high-accuracy true streaming Automatic Speech Recognition (ASR) model that features fine-grained and configurable decoding chunks from 80 ms to 2 s.

audio → text · made by Netease Youdao

Sold by

Nobody in the catalogue publishes a price for this yet.

About

Confucius4-R2T2 — a text model from Netease Youdao.

It takes audio and returns text. It was published in September 2026. The catalogue files it under transcribe. Its weights are published under the other licence, which attaches conditions the plain open licences do not.

Every current figure

Maker
Netease Youdao
Register
model
Takes
audio
Returns
text
Published
September 2026
Parameters
2 billion · read from its own weights
Licence
other

Known as 1 name

netease-youdao/Confucius4-R2T2