Voice AI platform for Indian languages with speech-to-text, text-to-speech, and voice conversations
Daily standup drafts from GitHub and Linear, confirmed in your AI agent, delivered to your team in Slack or Google Chat
Stage
Not given
MVP
Founded
Not given
Not given
Based in
IN
Not given
Pricing model
Contact for pricing
Free
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.
Free during the public beta. Pricing will be announced before the beta ends. Open source under the MIT license.
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
Drafts standups from GitHub pull requests, reviews and commits
Includes Linear cards in draft
Automatic blocker routing to reviewers and managers
Requires manual confirmation before sending
One digest per team with timezone support
Accepts late submissions in digest thread
Works with Claude Code, Cursor, Codex, VS Code and terminal
Configuration as code with review
Read-only API with scopes and webhooks
Managers can access team data through AI agent
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
Drafts automatically from GitHub and Linear activity instead of requiring manual entry
Privacy-focused: suggested blockers only visible to individual, never shared with managers
Open source MIT license with self-hosting option
Configuration as code with version control and automated validation