See text.
Get text.
The best desktop OCR tool you’ll ever use — and the last one you’ll need to download. Two OCR engines, Azure-powered searchable PDF, an image editor with share links, and a full PDF toolkit. Point it at anything — an image, a PDF, your screen — and get clean text out. You’ll save hours every week.
Fifteen tools. One clean app.
Every feature is one click away on the dashboard. No wizards, no learning curve — just tools that do exactly what they promise.
“I built every feature here because I needed it myself. I use this tool daily — and I think you’ll love it too.”
One click. Any image or PDF. Clean text out.
Drop in a photo, scan, screenshot, or PDF — pick your engine, hit run. Results show up with confidence scores and automatic table detection. Copy to clipboard, save to text, or feed straight into the next step.
- Paddle AI for speed (local inference, GPU-accelerated if available)
- Tesseract fallback for scanned documents & older layouts
- Table detection with cell-level recognition
- Confidence score per block — see exactly what’s uncertain
- Input: PNG, JPG, JPEG, BMP, TIFF, GIF, WEBP, PDF
Batch, preprocess, and refine at scale.
Feed in a folder of scans and let Advanced OCR work through them. Preprocessing options clean up noisy originals before recognition — deskew rotated pages, remove alpha channels, threshold light scans, apply denoising.
- Multi-file batch processing with per-file progress
- Preprocessing: denoise, deskew, rotate, crop, threshold, remove alpha
- Language selection for more accurate recognition
- Confidence-threshold highlighting (green = confident, yellow = review)
- Export per file or combined — text, clipboard, or file
Turn flat scans into fully searchable PDFs.
Kaizen OCR connects to your own Azure Document Intelligence resource. Bring your key, and we generate selectable-text overlays directly on top of scanned pages. Choose the Read model for text+tables flow or Layout to preserve formatting.
- Outputs: searchable PDF, plain text, Markdown, HTML, or JSON
- Read model: $1.50 / 1000 pages · Layout: $10 / 1000 pages
- Keys stay local — stored in an encrypted SQLCipher DB on your machine
- Test-connection button so you know it works before burning quota
- No Azure key? The feature is gated, but the rest of the app works fully offline
Press a key. Read the screen.
Six customizable global hotkeys turn the system tray into your OCR command center. Capture the full screen or a region, instantly or with a delay, and route it to Simple or Advanced OCR depending on how much post-processing you want.
- Fullscreen capture + OCR — default
Ctrl + Shift + F6 - Region capture + OCR — draw a box on any screen
- Delayed variants — capture menus and dropdowns without the key closing them
- Screenshot-only modes — grab without running OCR
- Auto-routing: Simple OCR or Advanced OCR, your choice
- Auto-delete screenshots after 1 hour to keep the folder tidy
Every PDF operation you keep reaching for.
No browser uploads. No “free trial, now pay $9.99”. Just the PDF tools on your desktop.
Create PDF
Combine PDFs and images into one custom document. Reorder pages, insert blanks, add text annotations (9 positions, custom font/color).
Merge / Split
Combine multiple PDFs into one, or pull individual pages and ranges out into separate files. Preview before saving.
PDF to Text
Three extraction modes: direct (embedded text), Tesseract OCR, or Paddle OCR. Per-page status tracking, export to TXT or clipboard.
PDF to Image
Export every page as PNG, JPG, BMP, TIFF, or WEBP. Perfect for archival, web use, or feeding into image tools.
Add PDF password
AES-encrypt sensitive PDFs with a password. Fast, reversible, no re-uploading to sketchy online tools.
Remove PDF password
Strip password protection from PDFs you own — paste the password, done.
Extract images from PDF
Pull every embedded image out of a PDF as its own file. Useful for asset recovery, design handoff, or visual QA.
Convert files
Convert between PNG, JPG, BMP, TIFF, WEBP, GIF, and PDF in both directions. Batch-friendly.
Combine images
Stitch multiple images into one horizontal or vertical composite — handy for long receipts, chat logs, and multi-part scans.
Image Edit
Open any image in the built-in editor. Add text annotations (14–64px), draw colored rectangles, undo with Ctrl+Z. Mark up screenshots before sharing.
Share Link Pro
One click: upload your edited image, get a shareable link copied to clipboard. Perfect for bug reports, feedback, Slack threads — no file attachment needed.
Straighten, annotate, share — then OCR.
Image Deskew straightens skewed scans in one click. Combine Images stitches receipts and chat logs. And the built-in Image Editor lets you annotate captures with text and rectangles before sharing — perfect for bug reports, feedback, and quick visual notes.
- Auto-detect document edges and deskew with OpenCV perspective-transform
- Horizontal or vertical image stitching with preview
- Image Editor: add text annotations (font size 14–64px) and rectangles with custom colors
- Share Link (Pro): upload the edited image and copy a shareable URL to clipboard in one click
- Undo support (
Ctrl+Z) in the editor - Output to PNG, JPG, BMP, TIFF, or WEBP
Three engines, picked for the job.
Not every document wants the same OCR. Here’s how to pick.
| Paddle AI | Tesseract | Azure Doc Intel | |
|---|---|---|---|
| Speed | Fast (local, GPU if available) | Moderate (CPU) | Network-bound |
| Accuracy on clean text | Excellent | Very good | Excellent |
| Accuracy on scanned docs | Very good | Excellent | Excellent |
| Tables | Built-in detection | Limited | Best-in-class (Layout) |
| Searchable PDF | |||
| Offline | |||
| Cost | Free with app | Free with app | $1.50–$10 per 1000 pages (your Azure bill) |
| Best for | Day-to-day OCR, batch jobs | Older scans, specialty languages | Searchable PDFs, complex layouts |
Over 100 OCR languages, bundled
No downloads, no packs. English, Hindi, Chinese, Arabic, Cyrillic — and 100+ more included in the Tesseract data that ships with the app.
Pick your tier. Keep it forever.
Every plan has a free tier with real utility. Yearly if you want renewable; Lifetime if you want to pay once.
Free
- 7 ops per feature
- Paddle AI + Tesseract OCR
- All PDF tools
- Screenshot capture & hotkeys
- 100+ OCR languages
- Searchable PDF (Azure)
Pro
- Everything in Free
- Unlimited ops across every feature
- Searchable PDF via Azure (BYOK)
- Priority email support
- Free upgrades during subscription
- Cancel anytime
Lifetime
- Everything in Pro
- No renewals, ever
- Lifetime updates
- Transferable between your devices
- Priority support
Free vs Pro / Lifetime
| Feature | Free | Pro / Premium |
|---|---|---|
| Simple OCR (Paddle + Tesseract) | 7 / feature | Unlimited |
| Advanced OCR (batch, preprocessing) | 7 / feature | Unlimited |
| All PDF tools (create, split, password, etc.) | 7 / feature | Unlimited |
| Image tools (deskew, combine, convert) | 7 / feature | Unlimited |
| Screenshot capture + global hotkeys | ||
| Image Edit (annotate with text + rectangles) | ||
| Share Link (upload & copy shareable URL) | ||
| Searchable PDF (Azure Doc Intel, BYOK) | ||
| Priority email support | ||
| License | Forever free | Yearly or lifetime |
Common questions
Read model is $1.50 per 1000 pages, Layout is $10 per 1000 pages. Azure also offers a free tier (500 pages/month on F0) which is usually enough for personal use. We don’t take a cut. Setup guide here.Know first. Get more.
Join our WhatsApp community for early access, free license giveaways, and direct dev support. No spam, ever. Your number stays private.
Never shared. Leave anytime.