← Back to the wire

Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English

AchievementModelSep 26, 2026

Sarvam AI released Saaras V4, a speech recognition model covering all 22 scheduled Indian languages plus English, available through its API at ₹30 per hour. The encoder-decoder system uses Sarvam-3B, a 3B-parameter hybrid state-space decoder trained in-house. Sarvam reports state-of-the-art accuracy across the 22 languages, and 16.03% WER on IndicContextEval L5 with keyterm prompting. All benchmarks are vendor-reported; independent reproduction has not been published. Weights are not public—self-hosting docs cover Saaras v3 only.

Receipt № 21041 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

Hugging FaceCompanySarvam AICompanyAI4BharatCompanySaaras V4ModelSarvam-3BModelSaaras v3Model
Canonical: https://www.marktechpost.com/2026/09/26/sarvam-ai-releases-saaras-v4-a-speech-to-text-model-for-all-22-indian-languages-and-global-english/