←Back to NewsAI News/AudionewsAudioLlmsGoogle's Gemini 3.5 Transcribe Hits 2.6% Error Rate and Reads Your ScreenGoogle's new speech-to-text model hits 2.6% word error rate, adds screen-aware context in Antigravity, and ships behind two developer APIs.SourceGoogle AntigravityPublishedAug 26, 2026, 5:03 PMAuthorAlphaSignal NewsroomRead1 min readGoogle's new speech-to-text model hits 2.6% word error rate, adds screen-aware context in Antigravity, and ships behind two developer APIs.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsQwen · newsAlibaba's Qwen3.8 LiveTranslate Cuts Speech Translation Lag to 2.3 SecondsAlphaSignal · paperResearchers Found a 'Pain Axis' That Makes Qwen 2.5 Pay for ReliefSpaceXAI · newsxAI Ships Grok Voice Transcribe 2.0 With Half the Errors at Same Price
