OCR
Image → selectable text
What is OCR?
Optical character recognition for images and scanned PDFs, running on your device via Tesseract.js. Same engine as PDF OCR — listed separately for users searching specifically for "AI OCR" or image-first OCR workflows. Languages supported: English, Spanish, French, German, Italian, Portuguese (more can be added).
How do I use OCR?
- Drop an image or PDF file.
- Pick a language.
- Let the Tesseract model download on first use (~10 MB), then watch recognition progress.
- Copy or download the extracted text.
When should I use OCR?
AI OCR and PDF OCR share the same engine — pick whichever URL users search for. For non-text image tasks (e.g. background removal), a different tool is needed; Background Remover is planned for a future phase.
How is this different from PDF OCR?
Same engine (Tesseract.js). PDF OCR is optimised for multi-page scanned documents; AI OCR is for single images and screenshots. Pick whichever matches your workflow.
Which file formats can I upload?
PNG, JPG, WebP, and single-page PDFs. Multi-page PDFs are handled by the PDF OCR tool.
Is my image sent to a server?
No — Tesseract runs entirely in your browser. The image never leaves your device, and the recognised text is not logged.
Is my file uploaded anywhere?
No. Everything runs in your browser. Your files never leave your device, and there is no server component for this tool.