french image to text
Copy French text from any photo, screenshot or scanned PDF — get editable Latin text in seconds.
First use downloads about 4.7 MB (OCR engine + language model). After that it's cached and works offline.
About French OCR
Bonjour le monde
The French model knows accented letters (é, è, ê, à, ç, œ) and French words, so it's more accurate than the English model on French text, which would often drop or mangle accents.
Use it for French textbooks, letters, menus and screenshots. Add English if the document mixes both languages.
Tips for accurate French text
- Accents are small marks — a sharp image keeps é and è distinct.
- Guillemets « » and apostrophes are recognised; check them before reusing the text.
- Crop to the text you need and avoid shadows across the page.
How it works
The tool runs Tesseract's neural-network (LSTM) French model directly in your browser. Small images are enlarged first, because OCR works best when letters are 20–40 pixels tall. The first time you use it, your browser downloads the OCR engine (about 4 MB) and the French model (about 0.7 MB); after that, everything loads from cache. You get plain Unicode text that you can edit, copy, or download as a .txt file.
Other languages
- English OCR
- Hindi OCR
- Marathi OCR
- Tamil OCR
- Telugu OCR
- Bengali OCR
- Gujarati OCR
- Kannada OCR
- Malayalam OCR
- Punjabi (Gurmukhi) OCR
- Urdu OCR
- Arabic OCR
- Spanish OCR
- German OCR
Frequently asked questions
Why not just use English OCR for French?
The English model doesn't expect accents and French words, so it makes more mistakes. The French model fixes that.
Is French OCR free?
Yes. There's no sign-up or page limit. The French model (about 0.7 MB) downloads once and is cached by your browser.
Are my images uploaded to a server?
No. Recognition runs on your device using WebAssembly. Your images and PDFs never leave your browser.
Can I convert a French PDF to text?
Yes. Drop the PDF — each page is rendered and read in your browser, up to 30 pages at a time.