Image to text (OCR)
Turn a photo, screenshot or scanned page into editable text. The Tesseract OCR engine runs inside your browser, so images are never uploaded. Supports English, Russian, Polish, Turkish, Spanish, Portuguese, Indonesian, Vietnamese and more.
Your files never leave your browser
How to use
- 1
Pick the language of the text in the image.
- 2
Drop a JPG, PNG or WebP — recognition starts automatically.
- 3
Copy the text or download it as a .txt file.
FAQ
Is my image uploaded?
No. OCR runs locally with Tesseract compiled to WebAssembly. The language data (2–3 MB) is downloaded once and cached.
How accurate is it?
Very good on clear, horizontal printed text and screenshots. Handwriting, low resolution or heavy skew reduce accuracy — crop and straighten the image first for best results.
Which languages are supported?
English, Russian, Ukrainian, Polish, Turkish, Spanish, Portuguese, Indonesian, Vietnamese, German, French and Italian. Pick the one matching the text.
Can I extract text from a PDF?
For PDFs with real text use PDF to text. For scanned PDFs, convert a page with PDF to JPG and run it through this tool.
Why is the first run slow?
The engine and language pack are fetched on first use. Later runs take a few seconds per image.