Extract Text (OCR)
Pull the text out of scanned PDFs and photos with OCR that runs entirely on your device, in Hebrew, English, or both at once. Nothing is ever uploaded.
- Drop a scanned PDF, or a JPG or PNG photo
- The text is recognized page by page, on your device
- Copy the text, or download it as a .txt file
0 bytes left your browserWhy is this limited?
Frequently asked questions
- Is my document uploaded for OCR?
- No. The recognition engine runs inside your browser: pages are rendered and read on your device, and neither the document nor the extracted text ever touches a server.
- Which languages does it recognize?
- Hebrew, English, and a combined mode that reads both in one pass, which is what most Israeli documents need: Hebrew prose around Latin names, amounts and web addresses. Choose the language before you start, because OCR does not detect it for you: the wrong model returns plausible-looking nonsense rather than an error.
- Does it work offline?
- Yes. The first time you use the tool, your browser downloads the recognition model (about 8MB) once and caches it. From then on, text extraction works even with no internet connection.