OCR Image to Text
Turn the words in a picture into text you can copy. Upload a photo, scan or screenshot and the built-in OCR engine reads the English text right in your browser — nothing is uploaded.
Your file is processed locally in your browser and never uploaded.
For best results use a sharp, well-lit image with clear printed text. Handwriting is not recognised reliably.
Your result will appear here
Extracted text
How to use
- Upload an image that contains clear printed English text — a document scan, photo or screenshot.
- Click Extract text. The OCR engine loads on first use (about 9 MB, once) and then reads the image.
- Copy the recognised text, or download it as a .txt file.
Frequently asked questions
Is my image uploaded to a server?
No. The OCR engine (Tesseract.js) runs entirely in your browser, and the image never leaves your device. The engine files are stored on this site, not on a third-party server.
Which language is recognised?
English only. The built-in language data covers English printed text. Other languages are not included, to keep the download small.
Why did some words come out wrong?
OCR works best on sharp, high-contrast printed text. Blurry photos, unusual fonts, rotated text and handwriting all lower accuracy. Try a clearer, straight-on photo of the text.
Does this work offline?
After the page and the OCR engine have loaded once, the extraction itself needs no network. Note that the OCR engine uses a web worker, so the page must be opened from a website (as here) rather than directly as a file on disk in some browsers.