Extract text from a scanned PDF (OCR)
Recognize and extract the text contained in your scanned document's images.
⬆
Drop your PDF here, or click to browse
One file at a time (50 MB max)
OCR (optical character recognition) extracts the text contained in a scanned PDF or image, where a simple copy-paste doesn't work.
How to extract text from a scan
- 1Upload your scanned PDF — The document containing the scanned pages is loaded into the tool.
- 2Choose the language — Select the text's main language for more accurate recognition.
- 3Start recognition — Each page is analyzed one by one; progress is shown in real time.
- 4Download the text — The recognized text for the whole document is bundled into a downloadable .txt file.
Why use this tool?
- ✓ Works on scans where the text isn't selectable.
- ✓ Supports French, English, and Spanish.
- ✓ The scanned document stays on your device; only a generic language model is downloaded.
Frequently asked questions
Is the recognition perfect?
Accuracy depends on scan quality; a sharp, well-contrasted document gives the best results.
Is my document sent to a server?
No, each page's image is analyzed directly in your browser; only a generic language model (unrelated to your content) is downloaded the first time.