Introducing Saaras V4, our most capable speech to text model yet.
This is a AI post classified by Jev as Voice AI (a model release), kept by the AI Radar because it carries real work, not commentary.
Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog: https://www.sarvam.ai/blogs/introducing-saaras-v4
Posted by Sarvam (85k followers) 1 h ago · 68 likes · 2.1k views · view the original post on X. Kept by the AI Radar as Voice AI.
More AI work like this
- Our transcription and audio cleanup models are now faster on Mac. — @desertantlabs
- New model leak: qwen-audio-3.1-realtime — @aitrackerbot
- New model leak: qwen-audio-3.1-asr — @aitrackerbot
- New model leak: qwen-audio-3.1 — @aitrackerbot
- ⚡ Meet Qwen-Audio-3.1! ASR, TTS & Realtime are fully upgraded, joined by two new models:… — @Alibaba_Qwen
- Meet parakeet-redux: a speech recognition model that runs on CPU and Apple Silicon. It's… — @HuggingModels
- Moving your voice agent off Vapi shouldn't mean rebuilding it. — @telnyx
- >hey, Opus 5.5 make a duet where one voice plays a melody forwards and the other plays… — @literallydenis
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 44.3k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 12:57 UTC. Full method.