← MDifying document to Markdown converter
Drop a PNG, JPEG, WebP, GIF or BMP — a screenshot, a photo of a page, a scanned document — and MDifying reads the text out of it with OCR and returns Markdown. The recognition runs in your browser, so the image is never uploaded.
Convert a file now — it is free and runs in your browser
Most free OCR tools work by uploading your image to a server. That is a meaningful difference when the page you are scanning is a payslip, a medical letter or a contract. MDifying runs the recognition engine as WebAssembly in the browser and serves its language models from this site, so the image stays where it started.
The trade is speed: the first run downloads the language models, and recognition takes noticeably longer than reading a text-based file.
OCR reads English and Spanish. Accuracy depends on the image: a straight, well-lit, in-focus page at a reasonable resolution reads well; a skewed phone photo in poor light does not. Handwriting is not recognised. Always read the output before relying on it — OCR mistakes look like ordinary text, which makes them easy to miss.