Sarvam AI Debuts Saaras V4, an ASR System Spanning 22 Indian Languages and English
Sarvam AI has introduced Saaras V4, a speech recognition system that supports the 22 scheduled Indian languages and English, including global accents. The model combines an audio encoder with a 3B hybrid state-space decoder and offers keyterm prompting, multiple output modes, and low-latency streaming. It is accessible through Sarvam's API, though the reported benchmark results have not yet been independently verified.
Expanded Detail
EXPANDED:
Saaras V4 is Sarvam AI’s speech recognition release, covering the 22 scheduled Indian languages and English, including global English accents
Expanded detail and Context are AI-generated analysis; the linked article remains the authoritative source.
This summary is Al-enhanced to contain extended analysis and broader social context. The original is {NAME); the linked article is the authoritative source. Original headline: “Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English.” Browse more stories.