How to convert JPG to text
- Choose one or more images.
- Keep Plain text (TXT) ticked; tick Searchable PDF too if you want one.
- Select Run OCR.
- Copy the text or download the .txt files.
Worked example
In the OCR tests, a 2550×3300 px scan (US Letter at 300 DPI) is read back with the line INVOICE 2026 TOTAL 42.50 exactly and a confidence above 80 percent. An image named scan.jpg gives scan.txt.
Formats and limits
| Input | JPEG, PNG, WebP, TIFF, BMP |
|---|---|
| Output | TXT |
| Limits | Up to 100 pages per run. The first run downloads about 7 MB (recognition engine and English data) from this site. |
| Engine | tesseract.js 7 (LSTM) in a Web Worker; pdf.js page rendering at 300 DPI; pdf-lib text layer |
Limitations
- English only.
- Handwriting, very small text and skewed photos are recognized poorly.
- Up to 100 pages or images per run.
Questions
Which languages are recognized?
English only at the moment; the recognition data for other languages is not included.
Does it read handwriting?
Not reliably. Printed text gives the most dependable results; handwriting, very small text and skewed photos are recognized poorly.
Is my image uploaded?
No. The recognition engine, about 7 MB, is downloaded from this site the first time and runs in your browser.
Privacy
Runs on your device. Files and text are processed in this browser tab and are not uploaded.
This page opens the Scanned document OCR ready for this task. See the privacy policy for how toolsdocks handles data.