Connecting to Sapphire
Aligning the stars
Open your account in minutes and start trading with the tools, insights, and support you need to make informed decisions.
Extract text from a scanned PDF using OCR that runs on your device.
Drop your files here
or browse, or paste from clipboard
PDF files
Processed in your browser - never uploaded
Some PDFs are just pictures. When a document is scanned or photographed, each page is stored as an image, so the words you see on screen are not actually text a computer can select, search, or copy. Try to highlight them and you get nothing. The OCR PDF tool solves this by reading the image and turning it back into real, editable text you can copy or save as a .txt file.
OCR stands for Optical Character Recognition. This tool renders every page of your scanned PDF, looks at the shapes of the letters, and recognises the words, all on your own device. It runs entirely in your browser using a self-hosted engine (tesseract.js), which means your document is never uploaded to a server. The file stays on your computer from start to finish, so even sensitive scans like contracts, bank statements, or ID documents never leave your hands.
Think of it as the companion to our PDF to Text tool. PDF to Text is instant, but it only works when a PDF already contains a hidden text layer. If that tool comes back empty, your PDF is image-based, and this OCR tool is what you need instead. It is free, needs no sign-up, and works best on clear scans of printed text.
Open the OCR PDF tool
Go to the OCR PDF (Scanned to Text) tool in your browser. There is no account to create and nothing to install. On your very first run, the tool downloads a small OCR engine (around 5MB); this happens once and your browser keeps it cached for next time.
Add your scanned PDF
Drag your PDF onto the page or click to choose it from your device. Because everything runs locally, your file is loaded straight into your browser and is never sent anywhere. This tool is meant for scanned or image-based PDFs; if your PDF already has selectable text, the faster PDF to Text tool will do the job instantly.
Let it read each page
The tool renders every page and recognises the text on it, one page at a time. Larger documents and higher-resolution scans take a little longer, since all the processing happens on your own hardware rather than a remote server.
Review the recognised text
When it finishes, the extracted text appears on screen ready to check. OCR is very good with clear printed scans but not perfect, so it is worth a quick read to catch the occasional misread character, especially with faint print or unusual fonts.
Copy or download your text
Copy the text to your clipboard to paste into a document or email, or download it as a plain .txt file to keep. From there you can edit it freely in any text editor or word processor.
The OCR engine is self-hosted and runs entirely in your browser. Your scanned PDF is not uploaded, stored, or seen by anyone else, which makes it safe for private paperwork like statements, agreements, and personal records.
Normal PDF text tools only work when a hidden text layer exists. This tool actually reads the image, so it can pull text out of scans, photos of documents, and old photocopies that would otherwise come back completely empty.
You get real, editable text you can copy or download as a .txt file, with no watermarks, no sign-up, and no page limits imposed by a paid plan. Once it is text, you can search it, edit it, or reuse it however you like.
Everything works from a web page. After the one-time engine download, you can OCR documents whenever you need without extra software, subscriptions, or uploads.
Most online PDF tools upload your document to a server to process it. This one does not. Every operation runs inside your own browser using WebAssembly, so your files are read, processed, and saved locally - they are never transmitted, stored, or seen by Sapphire Broking or anyone else. That makes it safe to use with financial statements, contracts, and identity documents.
Keep going
