NetEase Youdao open-sources Confucius R2T2, a 2B real-time speech model with tunable latency

dr_cintas · x · 2026-09-17

NetEase Youdao released Confucius R2T2, an open-source 2B-parameter speech model that transcribes in real time with near-offline accuracy. Its streaming decoding chunks are tunable from 80ms to 2s, letting developers set their own latency-accuracy trade-off. Fully free to download and run.

Related event: NetEase Youdao Open-Sources 2B Streaming ASR Model Confucius R2T2(15 posts)→

Original post →

More from Multimodal

Multimodal channel →