Screenshot to text

Paste a screenshot with Ctrl+V (⌘V on a Mac) and get its text, ready to copy. Works for error dialogs, chat messages, slides, code in a video and anything else you can capture on screen. Free, no signup, nothing is uploaded.

Image (JPG, PNG, WebP, GIF, BMP)

No image yet. You can also drop a file on this box or paste a screenshot (Ctrl+V / ⌘V).

Language
Line breaks

Taking the screenshot

System	Copy a screen area to the clipboard
Windows	Win + Shift + S, select the area, then Ctrl+V here
macOS	Cmd + Ctrl + Shift + 4, select the area, then ⌘V here
ChromeOS	Ctrl + Shift + Show windows, then Ctrl+V here
Phone	Take the screenshot, then pick it with the file button

Screenshots are the easiest input for OCR: sharp, straight, high contrast. Crop to just the text you need for the cleanest result.

How it works

This page runs Tesseract, the open-source OCR engine first built at HP and later developed at Google, compiled to WebAssembly. The first time you use it, your browser downloads the engine and the language model (about 3 to 6 MB, then cached). After that, recognition happens on your device. Small images are enlarged before recognition, because Tesseract reads best when letters are at least 20 to 30 pixels tall.

Getting better results

Problem	What helps
Wrong or missing letters	Use a sharper, larger image: a crop of just the text beats a wide photo. Screenshots work best. For photos, shoot straight on, in good light.
Accents read wrong (é, ü, ñ)	Pick the document's language: each one has its own model. English, French, German, Spanish, Italian and Portuguese are available.
Nothing found	Handwriting, stylised logos and text on busy backgrounds are hard for any OCR. Try grayscale or cropping first.
Text in columns or tables	Columns usually come out one after another; table cells as words on a line. Crop one column at a time if the order matters.

Text from a web page instead of an image?

If your screenshot comes from a website, you don't need OCR: the text is already there. A PDF printed by a browser keeps every word selectable and searchable. The Shotmint API prints any URL or HTML in Chromium, as a PDF or as an image:

curl "https://shotmint.creasework.com/v1/pdf?url=https://example.com&format=A4" -H "X-API-Key: YOUR_KEY" -o page.pdf

Each render is 1 credit. €5 buys 2,000 with no subscription, and credits never expire. Try it without a key on URL to PDF or website screenshot.

Get 25 free renders a month API docs

FAQ

Is my image uploaded? No. The OCR engine runs as JavaScript and WebAssembly on this page, so receipts, IDs and private screenshots stay on your device. Only the engine files are downloaded, from this site.

Can it read a scanned PDF? Yes, on OCR PDF: it reads every page and gives you a searchable PDF plus the text. If the PDF already has a text layer, PDF to text is faster and exact.

Does it read handwriting? Neat block capitals sometimes, cursive rarely. Tesseract is trained on printed text.

Is it free? Is there a limit? Yes, free with no signup and no limit. Very large photos take longer on slow phones.

Screenshot to text

Taking the screenshot

How it works

Getting better results

Text from a web page instead of an image?

FAQ

Related tools