aiqbench takeAI Products

Sarvam AI has launched Saaras V4, a specialized speech-to-text model supporting 22 Indian languages and global English using a hybrid state-space architecture. The system achieves state-of-the-art accuracy on benchmark datasets while maintaining low latency streaming under 150 ms, offering a practical alternative to general-purpose models for regional language transcription needs.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

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

MarkTechPostSeptember 26, 20264 min read

Sarvam AI's Saaras V4 is a speech-to-text model covering all 22 Indian languages plus global English. It pairs an audio encoder with a 3B hybrid state-space decoder. It adds keyterm prompting for up to 50 terms, 5 output modes from 1 model, and streaming with first-token latency under 150 ms. It is available today through Sarvam's API at ₹30 per hour. The post Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English appeared first on MarkTechPost.

Sarvam AI has released Saaras V4, the newest generation of its speech recognition model. It covers all 22 scheduled Indian languages plus English, now including global English accents. Sarvam reports state-of-the-art accuracy across all 22 languages. Is it deployable? Yes, through Sarvam’s API today, using model="saaras:v4". Weights are not public, and Sarvam’s SageMaker self-hosting docs currently cover Saaras v3 only. Saaras V4 is an encoder-decoder system. An audio encoder converts the…

Excerpt shown under the publisher's RSS terms · 71 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article