Extract text from images and scanned PDFs — free, private, browser-based OCR
- Upload your image or scanned PDF
- Select the OCR language and optional preprocessing
- Review, edit, and export the extracted text
Proof: Supports 14 languages with client-side processing. Your files never leave your browser.
Extract text from photos, screenshots, scanned documents, and PDFs — entirely in your browser with no server uploads.
- Supports 14 languages: English, Spanish, French, German, Italian, Portuguese, and 8 more.
- Handles multi-page scanned PDFs with per-page text extraction and page separators.
- Built-in preprocessing: grayscale and high contrast modes to improve accuracy on poor scans.
Most free OCR tools upload your files to unknown servers, cap at one page, or bury results behind ads and signup walls. This tool runs entirely in your browser using WebAssembly — your files never leave your device.
Powered by Tesseract.js, the same open-source OCR engine used by Google and LibreOffice.
OCR Extractor
Upload an image or PDF below. Processing runs locally in your browser.
Drop an image or PDF here, or click to browse
JPEG, PNG, TIFF, WebP, BMP, or PDF — up to 20 MB
Your files never leave your browser. OCR processing runs locally using WebAssembly. No data is sent to any server.
Need to rename extracted files automatically?
renamed.to uses AI to rename and organize files based on their content.
How to extract text from images and scanned PDFs
1. Upload your file
Drop or select a JPEG, PNG, TIFF, WebP, BMP, or scanned PDF up to 20 MB. Multi-page PDFs up to 20 pages are processed page by page with clear separators in the output.
2. Choose language & settings
Select from 14 languages. Enable grayscale or high contrast preprocessing for better accuracy on poor scans.
3. Text is extracted locally
The Tesseract OCR engine runs in your browser via WebAssembly. No files are sent anywhere.
4. Edit and export
Review the extracted text, fix any OCR mistakes inline, then copy to clipboard or download as a .txt file.
OCR best practices
Use high-resolution scans
OCR accuracy improves dramatically with resolution. Aim for 300 DPI or higher. If scanning, use the highest quality setting available.
Try preprocessing for faded text
Enable high contrast mode for receipts, old documents, or faded printouts. Grayscale helps with color backgrounds that confuse OCR.
Check confidence scores
A confidence score below 60% usually means the scan quality is too low. Try rescanning at higher resolution or adjusting preprocessing settings.
Clean up results before sharing
OCR is never 100% accurate. Always review the output, especially for numbers, proper nouns, and special characters that OCR commonly misreads.
Organize your documents based on their content
Once you've extracted text from your documents, let renamed.to automatically organize and rename the files based on their content.
50 free renames to start. No credit card required.
Frequently asked questions
How accurate is this OCR tool?
Accuracy depends on image quality. Clear, high-resolution scans of printed text typically achieve 90-98% accuracy. Handwritten text, low-resolution images, and unusual fonts will produce lower accuracy. Use preprocessing options to improve results on difficult scans.
Are my files uploaded to a server?
No. All OCR processing runs locally in your browser using WebAssembly (Tesseract.js). Your files never leave your device. The only network requests are to load the OCR engine and language data from a public CDN on first use.
What image formats are supported?
JPEG, PNG, TIFF, WebP, and BMP images are supported, as well as scanned PDF documents up to 20 pages. Maximum file size is 20 MB.
Can I OCR text in other languages?
Yes. The tool supports 14 languages: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Chinese (Simplified), Japanese, Korean, Arabic, and Turkish. Select the language before running OCR for best results.
How can I improve OCR accuracy?
Three things help most: (1) use high-resolution scans (300+ DPI), (2) enable preprocessing options like grayscale and high contrast, and (3) ensure the document is well-lit and not skewed. For multi-page PDFs, each page is processed independently.
Related resources
View and strip hidden metadata from PDFs
Check filenames work across platforms
Preview file rename operations before executing
See and remove metadata from images
Browse the full collection of file management tools
50 free renames. Pay as you grow.