Fully self-hostable — the entire stack runs locally with no cloud dependency. Designed for air-gapped government hospital networks.
Every component — LLM inference, speech recognition, text-to-speech, OCR, and database — runs entirely on-premises. Zero patient data leaves the hospital network. Perfect for HIPAA, DISHA, and air-gapped deployments.
A voice-first workflow designed for patients of all literacy levels and ages.
Patient selects from 10 Indian languages. All subsequent interactions happen in their chosen language.
Authenticate with ABHA ID, Aadhaar number, or register as a new patient. Linked to ABDM.
Consent is read aloud by the kiosk in the patient's language. One tap to agree — no forms to read.
AI asks structured medical questions via voice. Patient speaks naturally — STT captures, LLM extracts symptoms, vitals, and history.
Upload prescriptions, lab reports, or discharge summaries. OCR extracts text, LLM structures it into a timeline.
Physician sees a structured SOAP summary with red-flag alerts, document timeline, and FHIR-ready data — before the patient walks in.