Extract printed text from screenshots, scans and photos using OCR that runs entirely in your browser. Your image is never sent to a server.
Printed text works well; handwriting is unreliable. For best results use a scan or screenshot with at least 12 px text height.
The recognition engine and the English language model (~6 MB total) download once, then your browser caches them.
No. Recognition happens locally with Tesseract.js compiled to WebAssembly.
Shrink JPG, PNG or WebP files to a target size without uploading them …
Scale an image by percentage, fit it to a longest side, or set an exac…
Crop to 1:1, 16:9, 4:3, 3:2 or 9:16 with one click, or type an exact p…
Convert between JPG, PNG and WebP in your browser. Set quality and cho…
Enlarge small images 2×, 3× or 4× with high-quality resampling and opt…
Stamp your name, logo text or copyright line onto a photo. Choose posi…