Voice AI platform for Indian languages with speech-to-text, text-to-speech, and voice conversations
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
IN
Pricing model
Not given
Contact for pricing
Pricing
Not given
Custom pricing. Billing is based on speech-to-text per second the session is open, text-to-speech per character, and Sutra per token from a prepaid wallet.
Key features
Chrome extension integration with ChatGPT, Claude, Gemini, Grok, DeepSeek and Kimi
MCP server for coding tools like Cursor and Claude Code
Python and TypeScript SDKs for custom agent integration
Save conversations, web pages, documents and connected app content
Review, correct and remove saved memory
Control which AI tools access specific memories
Export memory in documented formats
Local deployment option with Python 3.12 or 3.13
93.1% answer accuracy on LoCoMo benchmark
67% fewer tokens than full conversation history on LoCoMo
Speech-to-text transcription in 27 Indian languages and English
Text-to-speech with preset and cloned voices
Sutra conversation model with native Hindi and Hinglish support
Real-time language switching during calls
Voice activity detection and turn-taking support
Browser playground for voice testing
What makes it different
One unified memory across all your AI tools instead of separate memories in each
Complete user control: review, correct, delete and export your memory anytime
Runs hosted or locally on your own machine
Published benchmark method and results for transparency
Open source SDKs, CLI and MCP server on GitHub
Support for 27 Indian languages plus English in a single platform
Built specifically for how Indian languages are spoken and used
Language switching mid-call without dropping the conversation
Integrated voice platform combining speech, transcription and conversations
Low latency with transcript ready 0.6-0.75s after speaker stops