Turn any image into text.

Drop a screenshot, scan, or photo and pull out the words inside it — editable, copyable, and ready to use. The text recognition runs entirely in your browser, so your image is never uploaded.

Language

Drop an image here

or click to browse — you can also paste from the clipboard

JPEG · PNG · WebP · GIF · BMP

Preview

Choose a language above, then run OCR to extract the text. The recognized text appears below, ready to edit and copy.

First run: the recognition engine and the language data download once (a few MB) and are then cached by your browser, so later runs are fast.

Starting… 0%

Something went wrong

Recognized text

Copied

How image-to-text works

01 / STAYS LOCAL

Nothing is uploaded

Your image is read straight off your device. The recognition engine runs as WebAssembly inside your browser — the picture never touches a server.

02 / READS THE PIXELS

OCR finds the words

Optical Character Recognition scans the image, detects letters and words, and reconstructs them as real, selectable text you can edit.

03 / CACHED ONCE

Fast after the first run

The engine and your chosen language pack download a single time, then your browser caches them so every later run starts almost instantly.

Frequently asked questions

Is it free and private?

Yes. The text recognition runs in your browser — your image isn't uploaded.

What is OCR?

Optical Character Recognition: it reads the text inside an image and turns it into editable, copyable text.

Which images work best?

Clear, high-contrast scans or screenshots of printed text give the best accuracy.

Why is the first run slow?

The recognition engine and language data download once on first use, then they're cached.

Which languages are supported?

English by default, with several more selectable.

Will it be perfect?

OCR is very good but not flawless on low-quality or handwritten text, so a quick proofread helps.