OCR a PDF — Arabic and English
Turn a scanned PDF or photos into a searchable PDF, and copy the text out of it.
Your files are never uploaded. The OCR engine and the language data download once from a CDN the first time you use a language; recognition runs on your device.
Drop a scanned PDF or photos here
One PDF, or one or more images (JPG, PNG, WEBP).
Frequently asked questions
How do I make a scanned PDF searchable?
Choose your scanned PDF (or photos of pages), pick the language, and click "Recognize text". You get a new PDF that looks identical but has an invisible text layer, so you can search it, select text and copy it.
Does it really work with Arabic?
Yes. Choose "Arabic" or "Arabic + English". The recognised Arabic is stored in logical order, so searching and copying work in PDF viewers and in Word. Clear scans give the best results; handwriting and very decorative fonts are still difficult.
Is my file uploaded?
No. The PDF and images stay on your device. The only downloads are the OCR engine and the language data, which your browser fetches once from a CDN.
Will it change how my PDF looks?
No. For PDFs, the original pages are kept as they are and the text is added invisibly on top, so the quality and layout don't change.
Why is the first run slow?
The first time you use a language, the browser downloads its language data (a few MB) and starts the engine. After that it is cached. Long documents take about a few seconds per page.
How can I get better results?
Use a sharp, straight, well-lit scan, choose the right language, and try "High" quality for small print. Photos taken at an angle or with shadows are harder to read.
Can I get the plain text too?
Yes. After recognition you can copy the text or download it as a .txt file, in addition to the searchable PDF.