| What it does | Browser-based OCR tool for extracting text from PDFs and images
| Client-side WebAssembly SDK for compressing images and PDFs in the browser before upload
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| IN
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| Pricing | Free: 3 trial credits. Starter: $9.9/mo for 600 credits. Plus: $19.9/mo for 1500 credits. Pro: $39.9/mo for 3500 credits.
| Developer Free: $0/forever with unlimited client-side WASM engine, zero-config, target KB file bisection, and default "Powered by 100KB" backlink. Commercial License: $19/month (or $149/year, save 35%) for 100% unbranded license, automated domain whitelist lock, and high-precision biometric passport
|
|---|
| Key features | - Extract text from PDFs, images, scans, invoices, receipts, forms, and tables
- Preview recognized text before downloading
- Download as Word, TXT, or Markdown
- Support for JPG, PNG, TIFF, BMP, GIF, and WebP files
- Create editable DOCX with headings, paragraphs, lists, and tables
- Process files up to 50 MB
- Choose OCR model by quality and credit needs
- One prepaid credit balance across workflows
- High accuracy text extraction
- Fast generation
| - Target KB bisection - compresses files to exact size caps (50KB, 100KB, 200KB)
- Vector-preserving PDF compression - shrinks PDF streams while preserving text and fonts
- ICAO biometric passport photo cropping - 70% head ratio for visa compliance
- AI background removal - neural network-based transparent PNG cutouts
- Signature contrast sharpening - cleans signatures under 20KB
- Parallel batch processing - processes 100+ files concurrently without UI freezing
- AWS S3 and Cloudflare R2 integration - 1-line wrapper for cloud storage uploads
- Format conversion - HEIC to JPG, PNG to JPG, JPG to PNG, image to PDF
- PDF manipulation - merge, split, convert PDF to Word
- Stamp and watermark removal - removes scanner artifacts and digital stamps
|
|---|
| What makes it different | - Browser-based OCR without installing desktop software
- Clean text preview before downloading results
- Multiple download formats: Word, TXT, and Markdown
- Preserves document structure including headings, lists, and tables
- Single unified credit balance for multiple OCR workflows
| - 0ms cloud latency - all processing happens locally in browser RAM with no server involved
- Reduces AWS S3 bills by 85% - shrinks 15MB uploads to 100KB before upload
- Unified SDK replacing 5 open-source packages - single solution for PDF, image, and AI tools
- 18+ media and document engines included - comprehensive toolkit from compression to biometrics
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 6 ▼ −2 (down) since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 18 | 2 |
|---|
| Citation Flow (Majestic) | 25 | 21 |
|---|
| Referring domains (Majestic) | 57 | 28 |
|---|
OCRStack
100KB Developer