100% free no uploads no sign-up

urdu image to text

Copy Urdu text from any photo, screenshot or scanned PDF — get editable Perso-Arabic (Nastaliq) text in seconds. Urdu + English is pre-selected for mixed documents.

languages in the image (pick all that appear):
🔎drop an image or pdf → get textor tap to choose · or paste a screenshot (Ctrl+V)🔒 read on your device — your files never get uploaded

First use downloads about 7.9 MB (OCR engine + language models). After that it's cached and works offline.

About Urdu OCR

سلام دنیا

Urdu is written right to left, usually in the flowing Nastaliq style where letters slope and overlap. That's one of the hardest styles for any OCR engine, so expect more errors than with Hindi or English — Naskh-style Urdu (used on many websites) reads noticeably better.

Urdu + English is selected by default. The result box switches to right-to-left so the text reads naturally.

Tips for accurate Urdu text

How it works

The tool runs Tesseract's neural-network (LSTM) Urdu model directly in your browser. Small images are enlarged first, because OCR works best when letters are 20–40 pixels tall. The first time you use it, your browser downloads the OCR engine (about 4 MB) and the Urdu model (about 1 MB); after that, everything loads from cache. You get plain Unicode text that you can edit, copy, or download as a .txt file.

Other languages

Frequently asked questions

Why is Urdu less accurate?

Nastaliq letters slope and overlap, and small dots change meaning. OCR engines find this much harder than separated scripts.

Is Urdu OCR free?

Yes. There's no sign-up or page limit. The Urdu model (about 1 MB) downloads once and is cached by your browser.

Are my images uploaded to a server?

No. Recognition runs on your device using WebAssembly. Your images and PDFs never leave your browser.

Can I convert a Urdu PDF to text?

Yes. Drop the PDF — each page is rendered and read in your browser, up to 30 pages at a time.