Image to text (OCR)

A whiteboard, a printed page or a signboard, turned into words you can copy.

Private: your files never leave this deviceNothing is uploaded or stored on a serverWorks right here in your browser

Thanks
LanguageEnglish
Line breaks

The engine and language data download once; images stay on this device. Scanned PDF? Use OCR PDF.

How to extract text from an image

  1. Add the images

    Drop photos, scans or screenshots on the box, choose them, or paste with Ctrl+V. Many at once is fine.

  2. Pick the language

    English is the default. Add Tamil, Hindi or any other language the text is in; up to three together.

  3. Copy or download

    Text for all images is gathered in one box with Copy and Download .txt. Each image also has its own text and a confidence score.

Good to know

  • Ctrl+C (Cmd+C on a Mac) with nothing selected copies the text of every image.
  • Crop to the part you need before you add a photo: less background means fewer stray characters.
  • For a sideways photo press the rotate button on that image; the text is read again the right way up.
  • Pick only the languages on the page. Each extra language slows the reading down and can swap look-alike letters.

Questions people ask

How do I copy text from an image?

Drop the image on the box, choose it, or press Ctrl+V (Cmd+V on a Mac) to paste a screenshot. The text appears a few seconds later. Press Copy, or Ctrl+C with nothing selected, to copy all of it.

Which languages can it read?

English, Tamil, Hindi, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, Punjabi, Urdu, Arabic, Chinese, Japanese, Korean, French, German, Spanish and more. Pick up to three at once for pages that mix scripts, such as Tamil with English.

How accurate is it?

Clear print, screenshots and flat scans usually come out almost word for word. Handwriting, very small or blurred text, curved pages and busy backgrounds do not. Each image shows a confidence score, and words the engine was unsure of are marked in amber on the preview so you know where to check.

Can I get the text out of a scanned PDF?

Use OCR PDF. It reads every page and gives you the same PDF back with a hidden text layer, so you can search and copy from it.

Are my images uploaded?

No. The text is read by Tesseract, an open-source OCR engine, running inside your browser. The first time, the browser downloads the engine and the language data (about 2 to 15 MB per language) once and keeps them for next time. Your images never leave your device.

Say thanks