OCR: image or PDF to text
Get the text out of a photo, a screenshot or a scanned PDF, in English or French. Copy it, or get a PDF you can search.
Accepted: JPG, JPEG, JFIF, PNG, WEBP, AVIF, HEIC, HEIF, GIF, SVG, BMP, TIF, TIFF, PDF · Max 190.7 MB per file
Processed on your device — nothing is uploaded.
How to extract text from an image or PDF
Drop your images (JPG, PNG, HEIC, TIFF…) or scanned PDFs above.
Pick the document language, then click Extract text.
Copy the text, download it as .txt, or get a searchable PDF.
How it works
- English and French
- Recognition runs on Tesseract, the leading open-source engine, with its English and French models. Accents, punctuation and numbers are recognised.
- Searchable PDF
- The PDF keeps exactly its original look: an invisible text layer is laid over each scanned page so you can search, select and copy.
- Nothing is uploaded
- Everything happens in your browser: your documents never leave your device. The engine is downloaded once, then cached.
- For best results
- Shoot flat, well lit and sharp. A 300 dpi scan gives excellent results; handwriting is still read poorly.
Related tools
- Image to textCopy the text from a photo, a screenshot or a photographed document instead of typing it again.
- Make a PDF searchableAdd a text layer to a scanned PDF so you can search, select and copy its text, without changing how it looks.
- PDF to WordTurn a PDF into an editable Word document to fix or reuse its text.
- Image to PDFTurn JPG, PNG, HEIC, WebP and other images into a single PDF. Choose page size and margins.
- Compress PDFMake your PDF lighter by recompressing its images while keeping text sharp.