← all releases
Sarvam AI·Feb 8, 2026·V3·open source
Saaras V3
Saaras V3 is Sarvam AI's latest Automatic Speech Recognition (ASR) model, designed to accurately transcribe speech in 22 Indian languages and English. It excels in handling code-mixed and noisy speech, providing real-time transcription with low latency.
AudioAgentic AI
overview
Saaras V3 is Sarvam AI's latest Automatic Speech Recognition (ASR) model, designed to accurately transcribe speech in 22 Indian languages and English. It excels in handling code-mixed and noisy speech, providing real-time transcription with low latency.
key features
- 01Multilingual support across 22 Indian languages and English
- 02Real-time transcription with low latency
- 03Enhanced accuracy for code-mixed and noisy speech
- 04Streaming architecture for immediate transcription
- 05Trained on over 1 million hours of diverse audio data
related productsbrowse all →
Agents UIopen sourceAgents UI is an open-source component library developed by LiveKit, designed to accelerate the creation of voice agent interfaces. Built with React and shadcn, it offers pre-built components for controlling input/output, managing sessions, rendering transcripts, and visualizing audio streams, enabling developers to build multi-modal, agentic applications on LiveKit's real-time platform.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.