Quick access

Saved in this browser. Sign in to keep it on all your devices.

Image to Text Converter (OCR)

Copy the text from photos, screenshots, and scanned PDFs in English, Bangla, Hindi, Arabic, and 25+ more languages. Paste a screenshot with Ctrl+V. Your files never leave your device.

Language of the text

Choose every language on the page, up to 3. The first run downloads about of language data; after that it’s instant.

Tips for better results

  • Take photos straight on, in good light, with the text filling the frame.
  • Crop away anything that isn’t text.
  • Printed and typed text works best. Handwriting usually doesn’t.

iPhone HEIC photo? Turn it into a JPG first with the HEIC to JPG converter.

Click to choose images or a PDF, or drop them here

Or paste a screenshot with Ctrl + V · JPG, PNG, WebP, GIF, BMP, PDF

Version 1.1 Updated What's new

Release notes

  1. v1.1 Latest
    • Added an in-depth guide below the tool, written from what the tool actually does.

About the Image to Text (OCR)

The image to text converter (OCR, optical character recognition) reads the words in a picture and gives them back as text you can copy, edit, and search. It works on photos of documents, screenshots, receipts, and scanned PDFs, in English and more than 25 other languages including Bangla, Hindi, Arabic, and Urdu.

How to use it

  1. 1 Pick the language of the text. Choose two if the page mixes languages.
  2. 2 Drop in images or a PDF, click to choose them, or paste a screenshot with Ctrl+V.
  3. 3 Copy the text, or download it as a .txt file.

Frequently asked questions

Are my images uploaded?

No. The text is read in your browser, so your images and documents never leave your device. Only the free OCR engine and the language data are downloaded the first time, then your browser keeps them.

Which languages can it read?

English, Bangla, Hindi, Arabic, Urdu, Persian, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Nepali, Chinese, Japanese, Korean, Spanish, French, German, Portuguese, Italian, Russian, Turkish, Indonesian, Malay, Vietnamese, and Thai. Pick up to three at once for mixed pages.

Can it read Bangla?

Yes. Choose Bangla (it is preselected on the Bangla OCR page) and printed বাংলা comes out as Unicode text you can paste into Word, Google Docs, or Facebook.

Can it read handwriting?

Not reliably. It is built for printed and typed text. Very neat block capitals sometimes work, but joined-up handwriting usually doesn’t.

How do I get the best results?

Use a sharp, well-lit image taken straight on, with the text filling most of the picture. Crop away anything that isn’t text and choose the right language. Small images are enlarged automatically before reading.

Can it read a scanned PDF?

Yes. Pages that already contain text are copied exactly, and scanned pages are read with OCR, one page at a time.

Is it free?

Yes, with no sign-up, no watermark, and no limit on the number of images.

Copying text from a screenshot

On Windows 11, the Snipping Tool has Text actions: take a snip, press the Text actions button and copy all the text. PowerToys Text Extractor (Win + Shift + T) grabs text from any part of the screen. On a Mac, Live Text lets you select words in screenshots opened in Preview or Photos, and phones offer the same with Google Lens and the iPhone camera. Use this page when you need a language those miss, such as Bangla or Urdu, when you have a batch of images or a scanned PDF, or when you want a .txt file at the end.

Photographing a document for a clean read

  • Lay the page flat on a dark surface, near a window, and turn the flash off to avoid a shiny patch.
  • Hold the phone parallel to the page, not at an angle, so the lines stay straight.
  • Take one page per photo and let the text fill the frame.
  • For a book, press the pages down near the spine, where the curve bends the lines.
  • Flatten a curled receipt under a glass or a ruler before you shoot it.

Tables, columns and receipts

OCR reads line by line, so a table comes back as rows of words separated by spaces. To get it into a spreadsheet, paste the text into Google Sheets or Excel and use Split text to columns, or Text to Columns, with space as the separator. Newspaper columns can get mixed together, so crop each column into its own image. On receipts, check the numbers by eye: a 0 read as O, a 1 read as l and a lost decimal point are the most common slips.

Where OCR mistakes come from

  • Low resolution: scan at 300 DPI, or take the photo closer, so that small print is not just a few pixels high.
  • The wrong language: an English-only read turns accented letters and other scripts into guesses.
  • Decorative, condensed or very thin fonts, and text printed over pictures.
  • Stamps, watermarks and signatures crossing the text.

Run a spell-check over the result before you use it, and read numbers, names and dates against the original.