Sarvam AI

Sarvam Vision v1.0

Sarvam Vision is a 3-billion parameter vision-language model developed by Sarvam AI, designed to perform a range of visual understanding tasks, including image captioning, scene text recognition, chart interpretation, and complex table parsing. It aims to address the challenges of document intelligence, particularly for Indian languages, by unlocking knowledge embedded in physical documents, scanned archives, and historical collections.

Sarvam Studio vBeta

Sarvam Studio is a comprehensive platform developed by Sarvam AI, designed to facilitate seamless content transformation across languages and formats. It enables teams to dub videos, translate documents, and manage multilingual content workflows within a unified workspace, ensuring the preservation of original meaning, structure, and intent. ([sarvam.ai](https://www.sarvam.ai/blogs/sarvam-studio/?utm_source=openai))

Bulbul V3 vv3

Bulbul V3 is Sarvam AI's latest text-to-speech model, designed to deliver natural, expressive, and production-ready voices for Indian languages. It leverages advanced language models to generate speech that aligns with the emotional content of the text, ensuring high listener preference and robustness across various input types.

Saaras V3 vV3

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.

Sarvam Arya

Sarvam Arya is an agent orchestration stack designed to make autonomous AI systems reliable for real-world production use. It addresses the infrastructure challenges in deploying AI agents at scale by providing a structured framework that ensures consistent and efficient execution.

Sarvam MCP Server v1.0.0

The Sarvam MCP Server is an official integration tool that exposes Sarvam's suite of public APIs—including speech-to-text, text-to-speech, translation, and large language models—as native tools for MCP-aware AI clients. It enables developers to integrate Sarvam's sovereign, India-focused AI capabilities directly into platforms like Claude Desktop, Cursor, and Windsurf with zero boilerplate code.

Sarvam Akshar

Sarvam Akshar is a document intelligence workbench developed by Sarvam AI, designed to enhance knowledge extraction from complex documents. Built upon the Sarvam Vision model, it enables grounded reasoning, layout-aware extraction, and automated proofreading, addressing challenges in processing unstructured documents.

Sarvam Edge v1.0

Sarvam Edge is an on-device intelligence platform developed by Sarvam AI, designed to bring AI capabilities directly to user devices without relying on cloud services. This approach ensures instant responses, enhanced privacy, and consistent performance regardless of network conditions. ([sarvam.ai](https://www.sarvam.ai/blogs/sarvam-edge?utm_source=openai))