PDF to text with OCR, in 24 languages

Get the text out of scanned PDFs, in English, Hindi, Marathi, Tamil, Telugu, Kannada, Malayalam, Bengali, Gujarati, Punjabi and more. Copy it, save it as a text file, or make the PDF searchable.

Runs in your browser. Your PDF is not uploaded, and there is no sign-up.

Features

What you get

Indian languages
Hindi, Marathi, Bengali, Tamil, Telugu, Kannada, Malayalam, Gujarati, Punjabi, Odia, Urdu, Sanskrit and Nepali, plus English and 10 more.
Smart reading
Pages that already have text are copied exactly. Only scanned pages are read with OCR.
Searchable PDF
Lay the read text invisibly over the scan, so the PDF can be searched and its text selected.
Sideways scans
A page scanned sideways is turned and read the right way.
Copy or save
Copy the text of one page or all of it, or save it as a .txt file.
Private
The reading happens on your device. Only the language files are downloaded, once.

How it works

Get the text in three steps

  1. Add your PDF

    Choose a PDF or drop it on the page.

  2. Choose the languages

    Pick the languages on the pages, up to three.

  3. Get the text

    Copy it, save it, or make a searchable PDF.

Get the text

Uses

When to use OCR

Old scanned documents

Turn certificates, letters and records into text you can edit.

Government forms and notices

Copy text from scanned Hindi or regional-language documents.

Study notes

Get printed notes and book pages into a document.

Searching scans

Make a scanned archive searchable.

Frequently Asked Questions (FAQ)

Have a scan you need as text?