Voice AI platform for Indian languages with speech-to-text, text-to-speech, and voice conversations
Stage
MVP
Not given
Founded
Not given
Not given
Based in
Not given
IN
Pricing model
Open source
Contact for pricing
Pricing
Free. The code is on GitHub under Apache 2.0. A future hosted team office feature will be paid.
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
Multi-agent monitoring from a single screen
Real-time status visualization with color-coded states
Tool approval and command authorization
Team workflows with task handoffs
In-conversation steering without window switching
System notifications for approval requests
Local-only architecture with no data leaving machine
Auto-deny protection for undecided requests
Integration with existing Claude subscription
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
Complete local-first privacy: code and transcripts never leave your machine
No configuration or learning curve: read a room and you can run it
Works with your existing Claude Code installation and subscription
Open source under Apache 2.0 with no account required
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