Sarvam(@SarvamAI):Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog:

Sarvam

@SarvamAI

Building the bedrock of Sovereign AI for India Experience Sarvam at

参加 June 2023

28 フォロー中 85.6K ファン

Sarvam@SarvamAI

2026.09.25 11:49

Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog: