Voice AI platform for Indian languages with speech-to-text, text-to-speech, and voice conversations
The framework for AI-generated electronics
Stage
Not given
Startup
Founded
Not given
Not given
Based in
IN
Not given
Pricing model
Contact for pricing
Open source
Pricing
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.
Not given
Key features
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
TSX components for circuits with props, children, and hooks
Real-time autorouting on 4-layer boards
AI coding skills for hardware with CLI and pre-fab context
Export PCB, schematic, and assembly images plus KiCad, DSN, JSON, and netlists
Visual diffs inside GitHub with native version control
Analog simulation with WebAssembly ngspice
First class KiCad support with native import and PCM export
Automatic part selection from real-time supplier integrations
Instant browser previews with schematic, PCB, and 3D view
50+ reference boards ready to fork
What makes it different
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
AI-native electronics design built as a TSX framework enabling agents to create circuit boards
Combines schematic capture and PCB layout design in one unified workflow
Web-first approach with instant browser-based previews and no IDE installation required