Now in private alpha · Computer vision · v0.1

Helping people understand the world through AI.

Point your phone at the world and it tells you what's there, out loud and as it happens. Handy for getting around, reading signs, and the everyday things sight makes easy.

Best on mobile · Allow camera access · Korean, English and Nepali supported

No download needed · Works in browser · Try in Korean: select 한국어

01 · The problem

The world isn't designed for everyone. Yet.

Every day, billions of people move through places that weren't built with them in mind. We're here to close some of that gap.

Navigation difficulties

Unfamiliar streets, big indoor spaces, crowded stations. They're all hard to move through when you can't see what's coming.

Accessibility barriers

1.3 billion people live with a disability. Most digital tools still aren't built around how they actually live.

Reading the world

Signs, menus, labels, a prescription bottle. So much of daily life is printed, and it's out of reach right when you need it.

Language limitations

Travelling, studying, an emergency. It all gets harder when the words around you are in a language you can't read.

02 · The solution

From live video to spoken guidance in milliseconds.

What you'd take in with a single glance, DrishtiLabs works out in about 40 milliseconds and says back to you, right away.

01

Camera

Captures the world as it is.

02

AI Processing

On-device vision models analyze the scene.

03

Real-time Understanding

It reads objects, text and distance, and works out what you're trying to do.

04

Voice Guidance

Natural, contextual narration in your language.

03 · Capabilities

One model. Six things it does well.

Wherever we can, it runs right on your device. That keeps it fast, and keeps your data with you.

Object Detection

Detects 1000+ everyday objects with bounding-box precision and depth estimation.

/ 01

Scene Understanding

It picks up how people, surfaces and spaces relate, not just what's in the frame.

/ 02

OCR Text Reading

Reads signs, menus, labels and documents aloud in real time.

/ 03

Voice Assistance

Clear, quick narration that still cuts through on a noisy street.

/ 04

Multilingual

Speaks 40+ languages and translates what's around you as you go.

/ 05

Accessibility First

Designed alongside the blind and low-vision community from day one.

/ 06

04 · How it works

From camera to spoken words, in four steps.

40msAI inference·300msfull end-to-end response
  1. 01

    Point the camera

    Open DrishtiLabs on your phone or wearable. The camera streams a live view to the model.

    drishti.live

    Camera online · 1080p · 30fps

  2. 02

    AI interprets the scene

    A vision-language model reads objects, depth, text and motion in under 40ms, with the full response back to you in about 300ms.

    drishti.live

    Detected: crosswalk, 2 pedestrians, traffic light (red)

  3. 03

    You get told what matters

    It only says what matters, clearly and calmly, in your language.

    drishti.live

    Wait. Red light. Two people on your left.

  4. 04

    Ask anything, anytime

    Tap or say a question. DrishtiLabs answers based on what it's seeing right now.

    drishti.live

    "What does that sign say?" → Emergency Exit

05 · Vision

Where we're headed next.

The tech that powers Drishti
Smart Glasses · Phase 4 Prototype
DrishtiLabs Prototype v2 — glasses frame with ESP32, OV2640 camera and wires, built in Kathmandu
Prototype v2

Prototype v2 · built in Kathmandu · ~12g · OV2640 camera · earbud audio (prototype) · bone conduction Phase 1 Korea

  1. Phase 1Completed

    Prototype

    Proof-of-concept vision pipeline with live narration.

  2. Phase 2In Progress

    MVP

    End-to-end product with onboarding and offline modes.

  3. Phase 3In Progress

    Mobile Application

    iOS and Android launch with wearable companions.

  4. Phase 4In Progress

    Smart Glasses

    Custom optics with always-on, hands-free guidance.

  5. Phase 5Vision

    Global Ecosystem

    Open accessibility platform for partners worldwide.

06 · Build logs

Built in public.

Subscribe to updates →
May 18, 2026Completed

Latency dropped to 38ms end-to-end

Rewrote the inference pipeline with quantized weights so narration feels instant.

May 11, 2026Completed

First outdoor walk with a beta user

DrishtiLabs guided a low-vision tester through a 1.2km route in Kathmandu with zero misses.

May 02, 2026Completed

Voice UI v2

Shipped a calmer narration style after 30+ interviews with accessibility advocates.

Apr 24, 2026Completed

OCR in low light

Trained a denoising adapter that improves sign reading accuracy by 22% at dusk.

07 · Team

Small team, big plans.

We're hiring researchers, engineers and accessibility specialists who care about this as much as we do.

RT

Rhythm Timalsina

Founder · CEO

Building AI that sees the world so more people can experience it.

SK

Shuva Kharel

Web & Backend

Keeps the backend fast and dependable, so the AI is there the moment you need it.

NB

Nishant Bhattarai

Research & Strategy

Connects the research with design that actually works for the people using it.

Open role

Be the next teammate.

Engineering, research, design and accessibility roles open.

Apply →

08 · Accessibility

We build accessibility in from the start.

We care about accessibility in the product and on this site too. We try to build it in from the start rather than bolt it on at the end, and we keep improving as we learn from the people we build for.

  • Keyboard navigation

    Every interactive element is reachable and operable with a keyboard alone, including a skip-to-content link.

  • Screen reader support

    Semantic HTML, landmarks and ARIA labels help assistive technologies announce content clearly.

  • Legible in light and dark

    Type, colour and spacing are chosen for legibility, and the site ships with fully themed light and dark modes.

  • Language accessibility

    The entire interface is available in English, Korean and Nepali, built on an i18n system designed to grow.

  • Responsive by design

    Layouts adapt fluidly from small phones to large desktops so content stays comfortable on any screen.

  • Continuous improvement

    Accessibility is an ongoing commitment. Found a barrier? The link below reaches us directly, and we keep refining.

Cross the Street Without Sight

An intense 30-second audio experience. Headphones on, eyes closed, only what you can hear.

Found an accessibility barrier? We genuinely want to know.

Tell us how we can do better

09 · Contact

Let's build sight together.

Investors, partners, accessibility experts, early testers. We'd love to hear from you.

dristhilabs@gmail.com

Kathmandu - Remote