OCR Photos to PDF

OCR (optical character recognition) reads the text in a photo and converts it into machine-readable characters. This tool applies OCR to your photos and packages the result as a searchable PDF — each photo becomes a PDF page with the recognised text embedded as a hidden, searchable layer.

Useful for whiteboard photos, handwritten meeting notes, business cards photographed on a phone, printed receipts, and any image where you later need to find or copy the text.

Select the language of the text in your photos before converting — accuracy improves significantly when the correct language model is used. English, Traditional Chinese, Simplified Chinese, Japanese, Spanish, French, and German are available.

All OCR runs locally in your browser using Tesseract.js. No image is transmitted to any server. The recognition model is cached after the first download, so subsequent conversions work even without an internet connection.