Recognise text (OCR)
Pulls the text out of a photo, a scan or a PDF made of images. You can have it as a text file or as a searchable PDF — the one where the document looks identical but the text can be searched and copied. The file never leaves your device: the recognition happens right here.
Your file stays on your device: nothing is uploaded
How it works
You give it a photo, a scan or an image-only PDF, and the text comes out. What it does not do: it does not straighten skewed photos, it does not preserve layout (columns and tables come out as lines), it does not read handwriting, and it recognises Italian and English. Automatic recognition never stops in front of a difficult image: when it does not understand, it guesses. That is why we always tell you how reliable the result is.
Frequently asked questions
- How many pages can a PDF have?
- Up to 50 per document, and you can add up to 20 files at a time. Each page takes a few seconds, so a long document needs a little patience. If your PDF runs past 50 pages, cut it up first with “Split PDF” and recognise the parts one at a time.
- My PDF already has selectable text. Is there any point?
- No. If you can select words in your PDF reader, the text is already there and you can copy it straight out. Here every page is read again as an image: the searchable PDF you get is made of page images, and the recognised text may contain mistakes the original didn’t.
- Can I tell where each page ends in the text file?
- Yes: in a multi-page document each page starts with a line such as “--- 3 ---”, carrying the original page number. Pages with no text are skipped. Within a page, line breaks stay where they were in the image: lines are not joined back into paragraphs.
- My pages are sideways or skewed. What can I do?
- Recognition does not straighten them for you, and crooked text reads worse. If it’s a PDF, rotate the pages in “Organise PDF pages” first, then bring it back here. If it’s a photo, take it again straighter and sharper: the result improves a great deal.
- My PDF is password-protected. Can it be read?
- Yes: a field to type the password appears in the file’s row, and the password stays on your device, like the file. If you choose the searchable PDF, the document you get is no longer protected: if you need it to be, put the password back with “Protect PDF”.
Your files are never uploaded. Anywhere.
Your file stays in your browser’s memory: it is read, processed and written back here. There is no server to send it to.
- Processed locallyEverything happens on your device.
- Nothing to upload, nothing to wait forNothing to upload, no waiting.
- No files to deleteWe keep nothing: nothing reaches us.