←Back to NewsAI News/AudiorepoAudioOpen SourceNetEase Youdao's Confucius4-R2T2 Streams Speech Without Ever Revising Committed WordsNetEase Youdao's open-source R2T2 streams speech to text with 200-600ms latency and never rewrites words it already emitted.SourceAlphaSignalPublishedSep 22, 2026, 11:17 AMAuthorAlphaSignal NewsroomRead1 min readNetEase Youdao's open-source R2T2 streams speech to text with 200-600ms latency and never rewrites words it already emitted.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsNVIDIA AI · newsNVIDIA's Nemotron 3 Beats 12 Rivals With a 14.72% Speaker Error RateTencent Hy · repoTencent's AuK Handles 16 Audio Tasks From a Single PromptTencent Hy · newsTencent's AuK Replaces 16 Speech Tools With One Open-Source Model
