A fast offline OCR tool for Windows. Grab any region of your screen, drop in an image, or open a PDF, and pull the text out. Everything runs locally, no cloud, no account.
- Screen Area Capture - click and drag across any region, works across multi-monitor setups with mixed DPI scaling.
- Image Upload - JPG, PNG, BMP, GIF, TIFF.
- PDF Input - digital PDFs use the embedded text layer directly (no OCR needed, instant). Scanned PDFs are rendered and OCR'd page by page.
- Batch Processing - queue any mix of images and PDFs, run them all, save individual files or one combined transcript.
- History - every extraction is saved with a thumbnail, timestamp, confidence, and settings. Re-OCR any past capture with different settings, or restore the text in one click.
- Offline OCR - powered by Tesseract, runs locally with no network calls.
- Page Layout Control - pick Auto, Single Column, Single Block, or Sparse Text to match the source.
- Auto-Enhance - upscales tiny captures and converts to grayscale before OCR for better results on small text and phone photos.
- Multiple Output Formats - copy to clipboard, save as plain text, Markdown (paragraphs preserved), or JSON with per-word confidence and bounding boxes.
- Cancellable - long PDFs and large batches can be stopped at any page boundary.
- Debug Panel - opt-in real-time log of every capture, OCR call, and error, exportable to TXT or CSV.
- Dark Theme - native dark title bar, indigo accent UI, custom scrollbar, themed dialogs throughout.
Made by EERIE | Support This Project | Report Issue | Feedback | Suggest Feature
