○ RUNS IN YOUR BROWSER

Image to Text (OCR)

Turn a screenshot, a photo of a page or a scanned document into text you can copy, edit and search. Drop an image or paste a screenshot, and the text appears next to it. The image is read on your own device and never uploaded.

IMAGE

TEXT

Add a photo or screenshot and the text in it shows up here. The image never leaves your browser.

Processed locally · 0 bytes sent

What this tool does

It finds the text in an image and gives it to you as plain text. It uses Tesseract, the open-source OCR engine first built at HP and later developed by Google, compiled to run inside your browser. Small screenshots are enlarged before reading and huge photos are shrunk, which makes the reading both more accurate and faster.

Good uses

  • Screenshots: copy text from an error message, a chat or a slide.
  • Documents: get the text out of a scanned letter, receipt or form.
  • Photos: copy a recipe, a sign or a page from a book.

Accuracy

On a clear screenshot, nearly every character comes through. Photos and scans depend on their quality, so check names, numbers and amounts before you use them. The status line under the tool says how sure the reader was. Everything runs on your device, so you can also use it for private documents.

Text recognition by Tesseract and tesseract.js, both under the Apache License 2.0.

How to copy text from an image

  1. 1

    Add the image

    Drop a JPG, PNG or WebP on the left, choose one from your device, or take a screenshot and paste it straight into the page with Ctrl+V (Cmd+V on a Mac).

  2. 2

    Wait while it reads

    The first time, your browser downloads the text reader, about 7 MB. After that, a screenshot takes a few seconds; a large photo can take a little longer.

  3. 3

    Check, copy or download the text

    Fix any wrong letters right in the text box, then copy it or save it as a .txt file. Turn on Join lines to get whole paragraphs instead of the line breaks from the image.

Frequently asked questions

Is my image uploaded?

No. The text recognition runs in your browser with Tesseract, an open-source OCR engine, so the image stays on your device. The page only downloads the engine and its English language data from this site; nothing goes the other way.

Which languages does it read?

English, for now. It also picks up numbers, email addresses and most punctuation. Text in other languages that use the Latin alphabet often comes through, but accented letters may be missed.

How do I get the best results?

Use a sharp, well-lit image with the text the right way up and in focus. Screenshots work best. Crop away pictures and backgrounds, and for a photo of a page, hold the camera straight above it. Handwriting and fancy fonts are hard for any OCR.

Can it read a PDF?

Not directly. Turn the PDF's pages into images with the PDF to JPG tool first, then add those images here. If you can select the text in your PDF viewer, it already contains text and you can copy it straight away.

Why do the lines break in odd places?

The text keeps the line breaks it had in the image. Turn on Join lines to merge the lines of each paragraph into one, which also puts words that were split with a hyphen back together.

On this page
Pages
Home
All tools
Suggest a tool
About
Privacy