Free tool
Urdu image to text, read on your device.
Marksheets, nikahnamas, notices, letters and book pages in اردو, read in your browser and given back as right-to-left Unicode text you can paste, search or translate. English and numbers on the same page are read too.
The first time, your browser fetches the reader: about 9 MB, and 1 to 6 MB for each other language. After that, a page takes a second or two, even a tilted phone photo.
Runs in your browser. Your files are never uploaded.
The text appears here, ready to copy or fix.
Several files, or a whole form? Tell Sochen “Read this scanned rent agreement and tell me the notice period and the deposit” and it does every step, checks each against the notification, and still keeps your files on your device.
Try Sochen free →How Urdu reads
- Urdu is written right to left and the letters join, changing shape by their position in a word. The reader handles the joining; you get plain Unicode letters, and the text box shows them right to left.
- Most Urdu print is Nastaliq, the hanging calligraphic style used by newspapers, books and many notices. The reader is trained mostly on Naskh-style type, so a Nastaliq page comes out with more errors than a Naskh one. Typed documents, forms and computer printouts in Naskh read best.
- Dots (nuqte) decide the letter: ب, پ, ت, ٹ, ث share one shape. On a faint scan a lost dot changes the letter. Names and unfamiliar words are where to check.
- Numbers may be Western 0–9 or Eastern Arabic-Indic digits (۰–۹). Both are read; each comes back as printed. English words in the text are read alongside.
Urdu documents people bring
- Marksheets and certificates from madrasa boards, Urdu-medium schools and universities.
- Nikahnamas, affidavits and letters typed in Urdu.
- Notices and forms from offices in Jammu and Kashmir, Telangana, Bihar and Uttar Pradesh, where Urdu is an official language.
- Pages of Urdu books, newspapers and poetry, to quote or translate.
Getting a better read
- Give it a typed or Naskh page where you can. For a Nastaliq newspaper, expect to correct several words a line, and prefer a sharp scan over a phone photo.
- Choose Urdu, not Arabic or Persian, for Urdu text. They share the script, but Urdu's extra letters (ٹ, ڈ, ڑ, ں, ے) are only in the Urdu model.
- Scan at 300 DPI or zoom the phone camera until a line fills the width. Dots are the first thing a soft scan loses.
- Handwriting, including hand-lettered Nastaliq, isn't read reliably. The reader is trained on printed type.
Worth switching on alongside Urdu: Nothing, unless the page mixes Hindi or another script. The reader takes up to three languages, and English is read with every Indian language automatically.
Scanned PDFs are read page by page, up to 30 pages at a time; a PDF with its own text layer is copied exactly, without reading the picture.