Tips for better OCR results
- Photograph the page flat, straight-on and in good light; avoid shadows and glare.
- Crop to the text you need with Crop Image first.
- Screenshots work best: they are perfectly sharp.
- For mixed English and Hindi documents, choose English + Hindi.
Related: JPG to PDF · PDF to JPG · compress PDF
How to use the Image to Text (OCR) tool
- Pick the language (English, Hindi or both).
- Choose, drop or paste (Ctrl+V) an image or scanned PDF.
- Wait a few seconds while the text is read.
- Copy the text or download it as a .txt file.
Why SaralKit?
- Free forever: no "credits", no trial, no premium tier, no watermark and no daily limit.
- No account, ever: nothing to sign up for. Just open the page and use it.
- No data stored: your files and the numbers you type are processed by your own browser. We never upload, store or see them.
- Works offline: once the page has loaded, most tools keep working without internet.
- Open source: anyone can read the code on GitHub.
Frequently asked questions
How do I extract text from an image?
Choose or paste an image (screenshot, photo of a document, scanned page) and the text appears in the box below. Copy it or download it as a .txt file.
Does it work for Hindi?
Yes. Choose Hindi or English + Hindi before adding the image. Printed text works best; handwriting is much harder for any OCR.
Can I convert a scanned PDF to text?
Yes. Drop a scanned PDF and the first 20 pages are read. To make a searchable PDF instead, that feature is on our roadmap.
How accurate is it?
Very good for clear printed text (often 95%+). Accuracy drops with blur, low light, unusual fonts, tables and handwriting. Always proofread important text.
Are my images uploaded?
No. The OCR engine (Tesseract, open source) runs inside your browser. It downloads once (about 5 MB) and then works offline.