PDF OCR
Turn a scanned PDF into a searchable document, in over 100 languages. Pages are rendered at 300 DPI, the language is detected from the script automatically, and the original page images are kept so the document still looks like the original. It is free, needs no account, and adds no watermark to your result.
PDF OCR
Add your files. Recommended settings are ready, so you can process in one click.
PDF, Word, images, audio, video, archives and more
Up to 100 files · 250 MB · No account- 1Add files
- 2Choose an action
- 3Download or keep going
What people use it for.
What happens to your file.
Each page is rendered at 300 DPI, the resolution Tesseract is trained for, then converted to greyscale with contrast normalised. Automatic script detection runs per scanned page, so a document can include different writing systems. A searchable text layer is written invisibly behind the original page image, so the document looks unchanged but is fully searchable.
Where it stops: Handwriting is not reliably recognised; this is built for printed and typed text. Very short snippets can fall back to English because script detection needs a reasonable amount of text, so set the language manually for a page with only a few words.
Everything you need, without a paywall.
Common questions.
Which languages are supported?
Over 100, covering every major writing system: Latin, Arabic, Cyrillic, Greek, Hebrew, Chinese, Japanese, Korean, Devanagari, Tamil, Thai, Amharic and many more. You can also combine languages for a mixed document.
Do I have to choose the language?
No. The script is detected from the page and the matching language is used. Choose manually if your document is very short, or if it mixes scripts and you want a specific combination.
Will the document still look the same?
Yes. The recognised text is added as an invisible layer behind the original page image, so the appearance is unchanged but the text is searchable and selectable.
Why is my OCR result poor?
Almost always input quality. Straighten the page with Deskew PDF first, scan at 300 DPI or higher, and make sure the contrast is good. A crooked or low-resolution scan limits any OCR engine.
You might also need.
Extract readable text from photos, screenshots and scanned images in over 100 languages, including Arabic, Chinese, Hindi, Japanese, Russian and every major script. Rotated, skewed and low-resolution pictures are corrected and enlarged before they are read.
Detect and correct small page rotation angles in scanned PDFs to make document pages straighter and easier to read or OCR.
Extract clean text from PDF files online. Copy your text instantly or download it as a TXT file for free.
Convert PDF text into structured Markdown with heading heuristics, paragraphs, lists and detected tables where available.