←Back to NewsAI News/AudionewsAudioBenchmarksSarvam Releases Saaras V4 to Transcribe All 22 Indian Languages at OnceSarvam's new speech-to-text model hits state-of-the-art on all 22 Indian languages plus seven English benchmarks, with five output modes in one model.SourceSarvamPublishedSep 25, 2026, 11:49 AMAuthorAlphaSignal NewsroomRead1 min readSarvam's new speech-to-text model hits state-of-the-art on all 22 Indian languages plus seven English benchmarks, with five output modes in one model.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsSarvam · newsSarvam's Saaras V4 Brings All 22 Indian Languages Into One ASR ModelArtificial Analysis · newsCartesia's Sonic 3.6 Dominates Eight of Nine Global Voice AI LeaderboardsArtificial Analysis · newsStepFun's StepAudio 3 ASR Tops Speech Benchmark With 1.7% Error Rate