No upload, 100% local, no account

OCR, extract text from images & PDFs

Drop an image or PDF and get the recognized text. The OCR runs entirely in your browser (on-device, offline after the first load), nothing is uploaded.

How OCR · image/PDF to text works

OCR, Optical Character Recognition, extracts text from scanned images and image-based PDFs and gives you a searchable, copyable result. Sunasty runs the Tesseract engine compiled to WebAssembly, loading the language model you select on demand.

Accuracy depends on the quality of your scan and the language selected. Crisp, high-contrast scans of printed text in a supported language typically yield excellent results; handwriting, low-resolution scans, pages with complex multi-column layouts or mixed scripts will be less accurate. Always review the output, particularly for names, numbers and technical terms. For best results, deskew the scan first with the PDF Deskew tool.

Frequently asked questions

How accurate is the OCR?

Accuracy varies with scan quality, resolution and language. Printed text scanned at 300 DPI or higher in a well-supported language (English, French, German, Spanish, and others) typically achieves high accuracy. Handwriting, low-contrast scans, unusual fonts and non-Latin scripts will produce more errors. Always proofread the output.

Which languages are supported?

Tesseract supports over 100 languages via its language pack system. Sunasty loads the language data you select directly in your browser; no data is sent to a server. Select the correct language before processing, mismatched language models significantly reduce accuracy.

Can it extract text from a multi-page PDF?

Yes. Each page is recognised in sequence and the extracted text is assembled into one output, page by page. Processing time scales with the number of pages and the complexity of each one.

Are my files uploaded to a server?

No. Recognition runs on the Tesseract engine compiled to WebAssembly, inside this browser tab; the language model (traineddata) is fetched once from Sunasty's own origin and cached, then your scan is read into memory on your device, recognised there, and the text appears locally. Your images are never transmitted to Sunasty or any third party. Open your browser DevTools, go to the Network tab and watch: no request carries your scan.

Does it work offline?

Yes, once the page has loaded. Because the processing happens on your device, you can disconnect from the network and the tool keeps working. This is the clearest proof that your data never leaves your machine.

Is it free? Do I need an account?

It is completely free and requires no sign-up. There are no watermarks, no daily limits and no tracking cookies needed to use the tool.