Features
100% on-device privacy, no cloud
Supports DeepSeek, Qwen, Llama, Gemma, Mistral, gpt-oss
Chat with PDF, image, and screenshot
Agent mode with autonomous multi-step tasks
Local web search within browser
Gmail assistant for summarization and replies
Writing tools for refine, rewrite, brainstorm
Immersive page translation
Right-click context menu integration
In-browser API for web apps
Image understanding with local Vision models
Open-source and auditable
Seamless Ollama integration
Text to Speech in 11 Indic languages with natural voices
Speech to Text (ASR) across 12 Indic languages
Translation across 23 languages
Document digitisation from PDFs and images into structured data
Dubbing capabilities for multimedia
Conversational AI agents (Samvaad) for voice and chat
Akshar document digitisation product
Arya AI for Work platform for enterprise workflows
Sovereign deployment: cloud, VPC, on-premises, air-gapped
Forward deployed engineering support for custom solutions
SOC 2 Type II, ISO 27001, DPDP Act compliant
Role-based access control and full audit trails
Models: Bulbul (TTS), Saaras (ASR), Mayura (Doc), Indus (LLM)
Python SDK (pip install sarvamai) and REST API
Playground for browser-based testing without setup
