OCR: Extract Text from an Image

Get the text out of a photo, a screenshot or a scanned document, in English, French, German or Spanish. Recognition runs in your browser: the image is never uploaded.

Drag your images here or click to choose themJPG, PNG, WebP, GIF, BMP… · you can also paste an image (Ctrl+V)

Text language

The first reading downloads the engine and the language (about 5 MB), then kept in cache. Words in orange are uncertain: check them. For a PDF, first turn its pages into images with the tool PDF to images.

Engine: Tesseract OCR (Apache 2.0), served from this site. Licences

Your images stay in your browser: they are never uploaded or stored.

Free · no sign-up

About this tool

This OCR (optical character recognition) tool reads the text in an image and turns it into editable text: a photo of a menu, a screenshot, a receipt, a scanned page, a label… It recognises English, French, German and Spanish, including accents.

Recognition runs entirely in your browser with the open-source Tesseract engine, hosted on this site: your images are never uploaded. You can process several images in a row, rotate an image, improve its legibility and see the recognised words right on the image, with uncertain words highlighted in orange.

  • Text extracted from a photo, screenshot or scan
  • English, French, German and Spanish, alone or combined
  • Several images in a row
  • Automatic enhancement: grey, contrast, upscaling
  • Recognised words shown on the image, uncertain ones in orange
  • Editable text, copy and TXT export, no upload

How to use it

  1. Import or paste one or more images.
  2. Tick the text language and choose the layout if needed.
  3. Click “Read the text”.
  4. Check the words in orange, then copy the text or download it.

Frequently asked questions

Why does the recognised text contain errors?

OCR depends on how sharp the image is: a blurry, tilted or low-contrast photo, or handwriting, gives poorer results. Rotate the image, turn on enhancement or crop to the text.

Can it read a PDF?

First turn the PDF pages into images with the PDF to images tool, then import them here.

Is handwriting recognised?

Tesseract is made for printed text; handwriting is usually not recognised well.

Are my images uploaded?

No, the engine runs in your browser; only the engine and the language are downloaded from this site on first use.

Related tools

See all 57 free tools →