# OCR: Image to Text OCR reads the text out of a photo, screenshot or scanned PDF so you can copy it as plain text. The recognition runs on your own device; nothing is uploaded. Canonical page: https://filetity.com/ocr ## Capabilities - Free: Yes, with no watermark and no page limit. - Account required: No. There is no account system. - Processed on device: Yes. The file is read by your browser and never uploaded. There is no server to send it to. - Formats: PNG, JPG, WEBP or PDF in. Plain text out, on screen and as a .txt download. A PDF is read page by page. - Limits: Printed text in Latin alphabets and Chinese. It does not read Arabic, Cyrillic, Korean, Japanese kana or Devanagari, and handwriting is hit and miss. Lines the model itself scored low are flagged, though a confident misread can still slip past the flags, so the output is shown for checking rather than downloaded blind. - Mobile: Yes, on any modern mobile browser. Large files are limited by the memory the phone gives the browser. - Offline: Yes, after the first use. The engine is about 9 MB and downloads once, then your browser keeps it, so later visits work with no network connection. ## Questions ### Can it extract text from an image or a screenshot? That is the whole job. Drop a photo, a screenshot, a scan or a page from a PDF and the words come back as text you can select and paste. A screenshot is the easiest case for it, because the letters are already crisp and evenly lit; a photograph of a page is harder and a photograph taken at an angle is harder still. It runs on your own device, so the picture is never uploaded, which matters when the thing you are copying text out of is a payslip or a letter. ### How accurate is it? On a clean screenshot or scan of printed text, close to perfect: our own rendered-page test came back 232 of 233 characters right, and the one miss was a space. On a deliberately noisy, tilted, low-quality photo of the same text it read 95 percent of the characters, and the mistakes it did make were confident ones the flags did not catch. That is the honest shape of OCR: very good, never guaranteed, so check numbers and names against the original. ### Can it read a scanned PDF? Yes. Each page is drawn to an image in your browser and the text is read out of the picture, which is exactly what a scan needs. A PDF that already has a text layer is better served by the PDF to Text tool, which copies the real characters instead of recognising them. ### Why is the download so big? The engine is a neural network, about 9 MB with its runtime, and reading letters out of pixels genuinely needs one. It downloads the first time you use the tool, from this site, and your browser caches it, so it is a one-time cost. Nobody who visits any other page on this site downloads a byte of it. ### Does it read handwriting? Sometimes, badly. The model is trained on printed text; neat block capitals often come out usable, cursive rarely does. Anything it does read from handwriting deserves a closer look than usual, and the confidence flags will usually tell you that themselves. ### What does a flagged line mean? That the model's own confidence for the weakest word on that line fell below 0.75. The engine already discards anything under 0.5 as not text; between those two numbers a line is usually real text with one wrong character in it. Check the flagged lines against the original before you trust them. ## Related tools - [PDF to Text](https://filetity.com/pdf-to-text): Pull the text out of a PDF, page by page, and copy it or save it as .txt. - [PDF to JPG](https://filetity.com/pdf-to-jpg): Turn each page of a PDF into a JPG image at the resolution you pick. - [Compress PDF](https://filetity.com/compress-pdf): Compress a PDF to a size you name, or to settings you choose.