Image to Text Converter (OCR)

Copy text out of a photo of a document, a scanned page, a screenshot or a sign. Choose the language, drop in the image and get editable text you can copy or download. Optical character recognition runs on your device with the open-source Tesseract engine.

How to extract text from an image

  1. Choose the language of the text (add a second language for mixed text, such as Hindi and English).
  2. Choose an image, drag it onto the box or paste a screenshot.
  3. Wait a few seconds, then copy or download the recognised text.

Tips for accurate results

Use a sharp, well-lit photo taken straight on. Crop away backgrounds and make sure the text is at least a few millimetres tall in the picture. Printed text works far better than handwriting.

Languages

Supports English, Hindi, Bengali, Marathi, Tamil, Telugu, Gujarati, Kannada, Malayalam, Punjabi, Urdu, Odia, the main European languages, Arabic, Chinese, Japanese, Korean and more. Language data (a few MB each) downloads once from jsDelivr and is cached.

Questions

Is the image uploaded?

No. Text recognition runs in your browser; only the open-source language data is downloaded.

Can it read handwriting?

Neat handwriting sometimes works, but the engine is designed for printed text.

Can I convert several images at once?

Yes. The text from each image is added one after another.

Related free tools