Building AyuSwar: Voice-First Health AI for Indian Languages

Dwivedula Samrudh — Sun, 01 Nov 2026 11:29:58 +0000

Picture a busy hospital OPD in India and the first five minutes of a consultation. The doctor types. The patient waits. Now make that patient a 70-year-old who is most comfortable in Telugu, speaking the half-Telugu, half-English mix that real consultations sound like. A text-first app can be a wall for people like that.

In an emergency, typing may not be an option at all. So I built AyuSwar (Ayu means life, Swar means voice) to explore one question: how far can voice alone take a health app? Speak to it in your language, and let it listen, understand and answer back.

Honesty up front: AyuSwar is a prototype built on synthetic data. It is not a medical device, it is not clinically validated, and it does not give diagnoses. In a real emergency, dial 112 or 108.

The architecture: Listen, Keywords, Risk, Guidance

Everything in AyuSwar hangs off one 4-stage pipeline. Each stage carries a status chip, and I want to be clear about what those chips are: they are my own labels for where each stage stands, not an independent audit. Here is what they currently say:

Listen (LIVE): ambient doctor-patient audio intake through the browser Web Speech API, with a local AudioContext FFT running alongside for signal analysis.
Keywords (DEMO): a hand-built mapping links colloquial vernacular idioms to WHO ICD-10 and SNOMED CT concept codes.
Risk (DEMO): non-diagnostic acoustic signal checks and triage urgency flags. Rules, not models, wherever safety matters.
Guidance (PLANNED): HL7 FHIR R4 document bundles and spoken prescription instructions in the patient's language.

The live /technology page draws this pipeline in real time, with LIVE, DEMO and PLANNED chips on each stage.

The hardest part: what patients actually say

Many patients do not say "I am experiencing palpitations". In my native Andhra, someone is more likely to say "గుండెల్లో దద" (gundello dada). So one core piece of the app is a vernacular mapping table: regional idioms in Telugu, Hindi, Tamil, Malayalam, Kannada, Marathi and Bengali, linked to standard clinical concept codes. This is a real excerpt from the repo:

// src/data/indicVernacularOntology.js (real excerpt, trimmed)
{
  id: 'ont_01',
  vernacular: 'గుండెల్లో దద',      // Telugu, Rayalaseema / Coastal Andhra
  transliteration: 'Gundello Dada',
  clinicalTerm: 'Palpitations & Cardiac Flutter',
  icd10: 'R00.2',                    // WHO ICD-10
  snomed: '80313002'                 // SNOMED CT
}

Two things to be clear about. First, this is a developer-authored mapping. I am a student builder, not a clinician, and the table is unvalidated: it is a structure waiting for clinician review, not an authority on symptoms. Second, that is exactly why it is plain data anyone can read and challenge on GitHub, instead of a black box.

Code-mixing is the default, not the edge case. A real sentence sounds like "doctor garu, naa chest lo burning sensation undi". Anything that only understands clean English or clean Telugu will fail people who speak like this, so the language handling assumes mixed input.

Audio-Rx and the rest of the system

The Audio-Rx studio turns a prescription into spoken instructions in the patient's own language, with word-by-word karaoke highlighting over colour-coded pill cards. It can then format the schedule as text and open WhatsApp with it ready to send; the send itself is always a human tap. The OPD Ambient Scribe drafts a structured SOAP note from a consultation conversation and is designed around a rule the site states openly: a doctor reviews before anything is exported. The Acoustic Signal Lab measures physical signal properties in the browser (F0, spectral centroid, energy flux) and labels itself on the page as non-diagnostic. The Sanjivani-108 emergency console triages a spoken distress call and prepares a hospital handover, with dispatch clearly marked as simulation and a 110 BPM CPR metronome on screen.

The Audio-Rx studio with sample medication cards - synthetic demo data, not real prescriptions and not medical advice. On-screen wording like "60 FPS" and "direct WhatsApp dispatch" is the site's own UI copy: aspirational, not measured performance, and the WhatsApp send is always a human tap.

The stack

Layer	Choice
Front end	React 19 + Vite on Vercel, installable PWA
Voice	Web Speech API; Gnani Prisma/Timbre adapters wired behind a browser-speech fallback (provider keys pending verification)
Acoustics	Web Audio API FFT in the browser: F0, spectral centroid, energy flux
Clinical vocabulary	Developer-authored Indic vernacular mapping to ICD-10 + SNOMED CT codes (unvalidated, open for review)
Maps	MapLibre GL + OpenStreetMap hospital discovery
Scanning	Tesseract.js OCR for blister strips and prescriptions
Mobile app	Planned: Capacitor dependencies are in place for an Android build, nothing built yet
Backend	Supabase-ready client; falls back to local demo storage when keys are unset

Testing the boundaries, not just the features

The most deliberate part of the codebase is the test suite, because much of it checks what the app must NOT do. Alongside the repo's Node test files, the /benchmarks page defines a contract-verification suite that runs in the browser against the app's own services; the assertions are written and wired, and I am still verifying a full green run end to end. They include: the assistant must refuse to prescribe drug doses, an emergency phrase must trigger a 112/108 warning, the acoustic analyzer must return isDiagnostic: false with a disclaimer, and no secrets may leak into the client bundle.

The /benchmarks runner is built to execute these assertions in the browser and export a software test report; a full verified green run is still in progress.

Most of my tests check what the app must never do.

What broke, and what I learned

Test on a phone early. Most users will meet AyuSwar on a small screen, and the first mobile feedback I got was blunt and useful: pages overflowing, a floating widget covering content, a whole route rendering blank.
Code-mixed speech is the default, not the edge case. Design for the half-Telugu, half-English sentence from day one.
Ask for the harsh review. An engineer at Gnani AI sent me a detailed list of what was wrong: numbers I could not evidence and claims the app could not keep. I have been cutting them since, some cleanup is still in progress, and the project is better for it.
Label reality. The simulated modules carry SIMULATION or DEMO labels, and the goal is a demo people can trust, not one that only impresses.

Honest limitations, and what is next

What is unfinished: the OPD scribe's full voice-capture pipeline is still under end-to-end test; the Gnani Prisma (speech-to-text) and Timbre (text-to-speech) adapters are wired with a browser-speech fallback while the deployed provider configuration is verified; and all patient data on the site is synthetic. The vernacular mapping needs review by someone with clinical training before I would trust it beyond a demo. Next steps are technical: finish the scribe pipeline, complete and verify the provider integration, expand the contract tests, and keep hardening the mobile layout.

Built for the Great Indian AI Internship Challenge 2026 by Gnani AI. All patient data shown is synthetic. #GreatIndianAIInternshipChallenge #GnaniAI

I Built an Interactive 365-Day Linux & SOC Analyst Master Platform (with Live In-Browser Labs & Threat Intel) 🚀

Dwivedula Samrudh — Thu, 20 Aug 2026 17:06:02 +0000

Learning Linux and transitioning into defensive cybersecurity (Blue Team / SOC Analyst) can be overwhelming.

Most tutorials stop at basic commands like ls, cd, and grep, while real-world SOC workflows (analyzing auth logs, writing detection rules, investigating phishing headers, mapping threats to MITRE ATT&CK) require complex virtual machines and expensive enterprise tools.

To bridge this gap, I built Linux SOC Handbook (My Linux Journey) — a free, interactive, zero-setup platform running 100% in your browser.

⚡ What is the Linux SOC Handbook?

It is a full 365-day structured curriculum paired with a 456-page Advanced SOC guide, live browser labs, a terminal emulator, threat intelligence lookups, and career interview prep.

🔗 Live App: https://my-linux-journey.vercel.app/

⭐ GitHub: https://github.com/Samrudh2006

🛠️ Key Features Breakdown

1. 📖 Dual Master Handbooks (800+ Pages)

365-Page Linux Handbook: Covers kernel architecture, process management, memory forensics, permissions, bash automation, and networking fundamentals.
456-Page Advanced SOC Guide: Deep dives into SIEM operations, Blue Team incident response, log telemetry, threat hunting, and digital forensics.

2. 🛡️ Live In-Browser SOC & Threat Labs

You don't need to spin up a heavy VirtualBox or Docker container to practice. The platform includes live browser simulators:

🔍 Log Parser Lab: Parse and extract anomalies from Syslog, Auth logs, and Apache/Nginx web logs.
🚨 Incident Labs: Step-by-step walkthroughs of live breach scenarios.
🛡️ Hardening Audit: Audit Linux server configurations against CIS benchmark standards.
📧 Phishing Inspector: Analyze raw email headers, SPF/DKIM/DMARC records, and malicious attachments.
🔑 Active Directory Log Lab: Analyze Kerberoasting and brute-force events (Event IDs 4624, 4625, 4768).
⚡ SOAR Playbooks: Automated triage and containment playbooks.

3. 📊 Threat Intel & MITRE ATT&CK Matrix

Interactive MITRE ATT&CK Enterprise Matrix navigation.
Live IOC Lookup (IP, Domain, File Hash reputation checkers).
Instant Quick Cheat Sheets for on-the-job command reference.

4. 🎯 Career & Certification Prep

200+ Curated SOC Analyst Interview Questions with detailed architectural answers and real-world triage scenarios.

5. 💻 Interactive Developer Experience

Built-in Live Terminal Simulator: Test commands right inside the page.
Audio Voice Notes: Listen to page explanations on the go.
Export to PDF & Offline PWA: Install on your phone or desktop and study offline.

💡 Example: Analyzing Auth Logs for Brute-Force Attacks

Here's a quick taste of the Linux log analysis techniques taught in the handbook:


bash
# Find top 10 IP addresses with failed SSH login attempts
grep "Failed password" /var/log/auth.log | awk '{print $(NF-3)}' | sort | uniq -c | sort -nr | head -10

# Detect users created with UID 0 (backdoor root users)
awk -F: '($3 == "0") {print $1}' /etc/passwd

# Check for open listening ports and associated processes
ss -tulpn

🚀 How to Try It
Everything is free and accessible with no login required:

👉 Explore the Platform: my-linux-journey.vercel.app

I would love to hear feedback from the DEV community!

What defensive labs or security tools would you like to see next?
Are you currently studying for CompTIA Security+, CySA+, BTL1, or Junior SOC roles?
Drop your thoughts and questions in the comments below! 👇

DEV Community: Dwivedula Samrudh