India · 30 October 2026
Available nowGnani AI launches Prisma v3.0 speech model for 10 languages
Gnani AI’s Prisma v3.0 supports Hindi, Bengali, Marathi, Gujarati, Punjabi, Kannada, Telugu, Tamil, Malayalam and English, and recorded a macro Word Error Rate of 16.93 on the Vistaar benchmark, beating ElevenLabs Scribe v2 (19.98), Microsoft Azure Speech‑to‑Text (20.51) and Deepgram Nova 3 (26.57). The model offers four transcription modes: Verbatim, Transcribe, Code‑mix and Transliterate.
Benchmarks are the company's own; not independently verified.
Why it matters
Prisma v3.0’s 16.93 macro WER sets a new low for multilingual ASR; plan features that rely on accurate mixed‑language transcription.
For product managers
For your product
What does this mean for your product?
Try it on your product More from this issueAll AI news from 30 Oct →
Get this every morning, written for your product.
Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.