Extract text from a scanned PDF
Runs optical character recognition on each page and gives you back a plain text file.
ℹ The scanning engine itself runs in your browser and your document is never uploaded anywhere. The one exception: the first time you use this tool, your browser downloads a small, generic, pre-trained English-language OCR model (a few MB, the same for every user) from a public CDN — this model contains no personal data, only pattern-recognition data for reading English text.
Drag & drop a PDF here, or
Large or many-page PDFs can take a while — OCR runs page by page, entirely on your device's CPU.