Make scanned PDFs searchable with private, device-aware OCR.
NewPDF Editor: change the text in a PDF, write and draw on itDrop a scanned PDF here or click to select
Your file never leaves your device · No signup · No daily limit
Up to 48 MB per file
OCR is where most tools paywall or upload: your scans (often the most sensitive documents you have) get processed on someone's server. Here Tesseract runs as WebAssembly in your browser, so the document never leaves your machine. Safety limits adapt to the device to prevent tab crashes.
No. The visible page content stays unchanged; only an invisible text layer is added above it.
Treat the output as a first draft, not a finished transcript. Pages are read at about 144 dpi regardless of how finely you scanned them, and on real-world documents some words are missed even when the scan looks clean, always read the result against the original before relying on it. Clear, high-contrast printed text does best; handwriting, low-resolution photos and heavy skew do worst. The tool skips words it is not reasonably confident about rather than inventing text.
