Image & PDF to text (OCR)
Reads the words out of a picture or a scanned PDF and hands you plain text you can copy. The recognition runs on your device.
Drop an image or PDF here
PNG · JPG · WebP · PDF — one at a time
Where do my files go?
Nowhere. The picture is read inside this browser tab and never uploaded. The one thing that does travel is the recognition engine itself, which is downloaded from a public CDN — your file goes the other way, which is to say nowhere.
Why does it download a few megabytes before it starts?
Because OCR needs a real engine and a trained model for the language you picked. Together that is roughly 4 to 6MB. We fetch it the moment you press the button and not before, and your browser keeps it afterwards, so the second document starts immediately.
Why isn't the text perfect?
We use the compact models, which are five to ten times smaller than the accurate ones (English: 2MB against 11MB, Japanese: 1.5MB against 16MB). On a clean scan the difference is small; on a blurry phone photo it shows. We would rather not make you download 16MB to find that out. Straighten the page and turn up the light and it improves a lot.
Can it read a PDF?
Yes, up to 30 pages at a time. Each page is drawn as an image first, then read. If the PDF already has real text in it, a copy-and-paste from any reader will be faster and exact — OCR is for the ones that are just pictures of paper.
Does it keep the layout?
No. You get the words in reading order, not columns, tables or headings. If the layout matters more than the words, this is the wrong tool.
Other tools
- Merge PDFSeveral PDFs into one, in the order you choose. Pages are copied, never re-rendered.
- Split PDFPull out the pages you want, or explode every page into its own PDF inside a ZIP.
- Rotate & delete pagesSee every page, turn the sideways ones upright and drop the ones you don't want.
- Compress PDFRe-compress the photos inside a PDF. The text stays text — nothing is flattened.