Image to text converter (OCR)

Copy text out of photos, screenshots, scanned documents and scanned PDFs. Optical character recognition (OCR) turns pictures of text into editable text.

IMGTXT

Choose images or scanned PDFs

or drop them here · JPG, PNG, WebP, PDF

Your files stay on your device. Nothing is uploaded.

About this Image to Text (OCR) tool

Typing out text from a photo of a notice, a screenshot, a printed letter or a scanned PDF is slow and error-prone. OCR reads the letters in the image and gives you real text that you can copy, edit, translate or search.

The recognition engine runs in your browser, so your documents stay private. English is built in, and Urdu, Arabic, Hindi, Bengali, Spanish, French, German, Portuguese, Russian, Turkish, Indonesian and Chinese can be added with one click. Scanned PDFs are supported too: each page is read in turn.

How to use Image to Text (OCR)

  1. Choose or drop your images or scanned PDF.
  2. Select the language of the text.
  3. Click Extract text. The first run downloads the recognition engine.
  4. Copy the text or download it as a .txt file.

Features

13 languages

Including Urdu, Arabic, Hindi and Chinese.

Scanned PDFs

Reads up to 50 pages per PDF.

Batch

Process several images at once.

Confidence score

Tells you when an image is hard to read.

Private

Recognition runs on your device.

Tips for accurate OCR

  • Use a sharp, well-lit image with the text straight and filling most of the picture.
  • Pick the correct language. Mixed-language documents work best with the main language selected.
  • Printed text works best. Neat handwriting may partially work; cursive handwriting usually won't.
  • For text-based (not scanned) PDFs, PDF to Text is faster and 100% accurate.

Frequently asked questions

How do I copy text from an image?

Choose the image, select the language and click Extract text. The recognised text appears in a box where you can copy it.

Can it read scanned PDFs?

Yes. Choose the PDF and each page is converted and read, up to 50 pages at a time.

Does it support Urdu and Arabic?

Yes. Select Urdu or Arabic from the language list. The language data downloads once, then it's cached by your browser.

Why is the first run slow?

The recognition engine and language data (a few megabytes) download the first time. Later runs start much faster.

Are my images uploaded?

No. OCR runs in your browser and your files never leave your device.

At a glance

Input
JPG, PNG, WebP, HEIC, PDF
Output
Text / TXT
Languages
13
Upload
None, runs in browser

Related tools

More free tools