Saaras V4: Sarvam AI’s new speech recognition model adds 22 Indian languages, 5 speech formats

T1Covered by 1 source · first reported by Mint — Technology / AI at 25 Sept, 04:41 UTC

Sarvam AI has launched Saaras V4, a new speech recognition model supporting 22 Indian languages and English. The model offers five output modes: transcription, translation, transliteration, verbatim and code-mixed text.

india

Sources

• T1Saaras V4: Sarvam AI’s new speech recognition model adds 22 Indian languages, 5 speech formatsMint — Technology / AI25 Sept, 04:41