Image to Text (OCR)

Copy the text of a screenshot or a photo.

  • Runs in your browser
  • Free
  • No sign up

You may also like

See all tools

Extract text from an image, without uploading it

This image to text converter reads the text of a screenshot, a photo or a scanned page with OCR (optical character recognition), and gives it back as text you can edit, copy or download. It runs in your browser: the image is never sent to a server, so it works with private documents too, and there is no daily limit. Keep the line breaks of the image, or join the lines of each paragraph to paste the text straight into a document.

How to convert an image to text

  1. Choose the language of the text (English by default).
  2. Drop an image, click to choose one, or paste a screenshot with Ctrl+V.
  3. Check the text, fix a word if needed, then copy it or download it as a .txt file.

What to use it for

  • Screenshots: copy the text of an error message, a slide, a video frame or an app that does not let you select it.
  • Photos of documents: a receipt, a letter, a page of a book or a whiteboard, turned into text you can search and edit.
  • Scans: get the text of a scanned contract or form without typing it again.
  • Notes and studies: quotes from a printed book, handouts, a menu or a poster in another language.
  • Accessibility: text that a screen reader or a translator can then use.

Tips for a better result

  • Crop the image to the text you need: less noise, fewer mistakes.
  • Take the photo straight above the page, in good light, without shadows.
  • Choose the right language: it knows the accents and the common words of that language.

Frequently asked questions

How do I copy text from an image?

Drop the image in the box, click to choose it, or paste a screenshot with Ctrl+V. The text is read in a few seconds and shows in a box you can edit. Click Copy text, or Download .txt to save it as a file.

Is my image uploaded?

No. The text recognition (Tesseract, an open source OCR engine) runs in your browser. The only thing downloaded is the recognition data of the language you choose, from a public CDN (jsDelivr), once: it is then kept in your browser for the next times. Your image and its text never leave your device.

Which languages can it read?

29 languages, among them English, French, Spanish, German, Italian, Portuguese, Dutch, Polish, Russian, Arabic, Hindi, Chinese, Japanese and Korean. Choose the language of the text before or after adding the image: the right language makes a big difference for accents and special letters.

Why are some words wrong?

OCR reads printed text best: sharp, straight, dark text on a light background. Blurry photos, text at an angle, small text, fancy fonts and handwriting give more mistakes. The tool shows a confidence score and warns you when it is low; the text stays editable so you can fix a word before copying it.

Can it read handwriting or a PDF?

It is made for printed and typed text: neat handwriting sometimes works, cursive rarely does. For a PDF, take a screenshot of the page and paste it here. Most PDFs made on a computer already contain their text: you can select and copy it directly.

Is it free, with a limit?

It is free, without sign up, watermark or monthly limit: since everything happens on your device, it costs us nothing per image.

Related tools

  • Word counter: count the words and characters of the text you extracted.
  • Image resizer: crop an image to the part with the text before reading it.