OCR – Image & PDF to Text
Extract text from images and PDFs with OCR — free, private, in your browser.
✓ Your files never leave your device. Everything runs locally in your browser.
OCR (Optical Character Recognition) reads the text inside an image or a scanned PDF and turns it into editable, copyable text. This tool runs OCR in your browser — no upload, which matters for receipts, IDs and contracts.
Images (PNG, JPG, WebP) and PDFs are supported; PDFs are rendered page by page and each page is recognised.
How it works
- Choose a file – Pick an image or a PDF that contains text.
- Choose the language – English or German — pick the language of the text for best accuracy.
- Convert – Click Convert to run OCR (this may take a few seconds).
- Copy or download – Copy the text or download it as a .txt file.
Tips for better accuracy
- Use a sharp, well-lit image or a text-based PDF.
- Straighten skewed scans if possible.
- Higher-resolution images usually recognise better.
- Match the language to the text.
Privacy
Receipts, invoices and ID documents are sensitive. Because recognition runs locally in your browser, nothing is uploaded — unlike most online OCR services.
Frequently asked questions
Are my files uploaded?
No. OCR runs entirely in your browser using a WebAssembly engine.
Which languages are supported?
English and German are included in this offline build.
Does it work on scanned PDFs?
Yes — PDF pages are rendered to images and then recognised.
Why is it slow the first time?
Your browser loads the OCR engine and language data on first use; later runs are faster.
Related tools
Extract text from your image or PDF now — free, private and without uploading it.