slopbin / image-to-text-ocr
free tool — runs in your browser

Image to text OCR

Drop in a screenshot, photo, or scan and pull out the text. Everything runs client-side — the image never leaves your machine.

Click to choose an image, or drag one here
JPG, PNG, WEBP — clearer, higher-res images read better
Preview of the selected image to be scanned for text
Reading image 0%

Extracted text

How it works

This tool uses Tesseract.js, an open-source OCR engine, running entirely inside your browser. No image is uploaded to a server — recognition happens on your device, so it works offline once the page has loaded and keeps whatever you scan private.

When it works best

Straight-on shots of printed or typed text — screenshots, scanned documents, book pages, receipts — give the cleanest results. Skewed angles, low resolution, and handwriting will reduce accuracy.

FAQ

Is my image uploaded anywhere?

No. The OCR engine runs entirely inside your browser using Tesseract.js. The image stays on your device — no server, no upload, no round-trip.

What languages are supported?

English only by default. Tesseract.js supports 100+ languages if you swap in additional traineddata files, but this tool ships with English to keep the first-load size small.

Does it work offline?

After the first load, subsequent scans run without an internet connection. The page and the OCR engine are both cached by your browser.

Can I scan handwriting?

Tesseract.js is trained primarily on printed text. Clear block-printed handwriting may work passably; cursive and messy handwriting generally will not.

What image formats are supported?

Any browser-readable image — JPG, PNG, WEBP, GIF, BMP. Clearer, higher-resolution scans give the best results.