Is this OCR really unlimited and free?

Yes. Recognition runs entirely inside your browser using the open-source Tesseract engine, so there is no server cost, no page cap and no account.

Can it turn a scanned PDF into a searchable PDF?

Yes. Enable 'Also build a searchable PDF' and every page keeps its original image while an invisible text layer is added underneath, so you can select, copy and search the text.

Which languages are supported?

English, Spanish, French, German, Portuguese, Italian, Dutch, Russian, Arabic, Hindi, Chinese (Simplified), Japanese and Korean. The language pack downloads once and is cached for later runs.

How do I get the best accuracy?

Choose the correct language, use a scan of at least 300 DPI, keep pages straight, and pick the 'Small print or blurry' quality option for difficult documents.

Do my documents get uploaded?

No. Files never leave your device — you can disconnect from the internet after the page loads and OCR still works.

OCR studio

Image to text: copy the words out of any JPG, PNG or scan

Drop a photo, screenshot, JPG, PNG or scanned PDF and get clean, editable text back. Most OCR tools cap you at a handful of pages or charge for a searchable PDF — this one runs in your browser, so it is unlimited, private and completely free.

Drop a scan, photo or PDF here

PNG, JPG, WEBP, TIFF or PDF — everything is read on your device

Unlimited pages

No 10-page trial wall, no watermark, no daily quota.

Searchable PDF

Keep the original scan and add a selectable text layer.

13 languages

Downloaded once, then cached for instant reuse offline.

Nothing uploaded

Confidential contracts and IDs stay on your machine.

How to extract text from a scan

1. Drop your image or scanned PDF into the box above.
2. Pick the document language and how clean the scan is.
3. Choose whether you also want a searchable PDF.
4. Press Extract text, then copy it or download .txt, .docx or the searchable PDF.

Frequently asked questions

Is this OCR really unlimited and free?: Yes. Recognition runs entirely inside your browser using the open-source Tesseract engine, so there is no server cost, no page cap and no account.
Can it turn a scanned PDF into a searchable PDF?: Yes. Enable 'Also build a searchable PDF' and every page keeps its original image while an invisible text layer is added underneath, so you can select, copy and search the text.
Which languages are supported?: English, Spanish, French, German, Portuguese, Italian, Dutch, Russian, Arabic, Hindi, Chinese (Simplified), Japanese and Korean. The language pack downloads once and is cached for later runs.
How do I get the best accuracy?: Choose the correct language, use a scan of at least 300 DPI, keep pages straight, and pick the 'Small print or blurry' quality option for difficult documents.
Do my documents get uploaded?: No. Files never leave your device — you can disconnect from the internet after the page loads and OCR still works.

Just have a photo or screenshot? Use the image to text converter.