Sarvam AI Releases Saaras V4 Speech Model Supporting 22 Indian Languages and Five Formats
Sarvam AI has launched Saaras V4, an advanced automatic speech recognition model supporting 22 Indian languages and English. The model processes speech in five formats—verbatim, transcribed, code-mixed, transliterated, and translated—directly within a single system, reducing errors from multiple processing stages. Designed to handle regional accents, dialects, and noisy audio, Saaras V4 offers low-latency streaming suitable for real-time applications. It incorporates a 3-billion-parameter hybrid language model and is accessible via API with Python and Node.js SDKs.
First-hand measurement across 2 sources
We measured how 2 outlets covered this story. No outlet gave this story a measurable political slant — there is no left–right reading to report. Overall sentiment is neutral (58/100). Lens Score 35/100.
Outlets measured: businessstandard, mint. See how each one headlined and framed the same story in the source comparison below.
AI Analysis
Sentiment was consistent across outlets (50–65/100), indicating broadly factual reporting rather than editorialising.
Coverage timeline
mint broke this story on 25 Sept, 04:51 am. Other outlets followed.
- 1