SnapText — Screenshot to Text

Tracking since Apr 28, 2026.

Changelog

• May 5, 2026
  description

  SnapText — Screenshot to Text
  
  Stop retyping what's already on your screen.
  
  SnapText lets you drag a selection over any part of any webpage — a table, a code block, a scanned image, a UI screenshot, a PDF preview — and instantly extracts every word from it. No copy-pasting. No manual transcription. Just select and read.
  
  ── How it works ──────────────────────────
  
  1. Click the SnapText icon in your toolbar
  2. Click "Capture Region" — your popup closes and a crosshair appears
  3. Drag to select any area on the page
  4. Text is extracted and copied to your clipboard automatically
  
  That's it. No forms. No upload dialogs. No waiting.
  
  ── Two OCR engines. You choose. ──────────
  
  ▸ Claude Vision (recommended)
     Powered by Anthropic's Claude — the most accurate OCR available. Handles complex layouts, mixed fonts, handwriting, math, tables, and code. Requires a free Anthropic API key.
  
  ▸ Tesseract.js (offline mode)
     Runs entirely inside your browser. No internet required after the first load. No API key. Great for privacy-sensitive content or when you're offline.
  
  ── What it's great for ───────────────────
  
  ✓ Copy text from images and screenshots
  ✓ Extract data from tables and charts
  ✓ Grab code from screencasts or tutorials
  ✓ Read locked PDFs displayed in the browser
  ✓ Transcribe handwritten notes
  ✓ Pull contact info from photos
  ✓ Digitize scanned documents
  ✓ Capture text from videos (pause and capture)
  
  ── Privacy first ──────────────────────────
  
  Your API key is stored locally in your browser and never leaves your device except when making a direct call to Anthropic's API. No analytics. No tracking. No servers in between. History is stored locally and you can clear it anytime.
  
  ── No subscription. No account. ───────────
  
  SnapText is free to use with Tesseract (offline mode) right away. For Claude Vision, you only need a free Anthropic API key — pay only for what you use, at Anthropic's standard rates (typically fractions of a cent per capture).
  
  Get your free API key at console.anthropic.com
  
  ────────────────────────────────────────
  
  Try it on any page in 30 seconds. Click "Add to Chrome" to get started.
  
  What's new?
  v1.1.0 — Complete rewrite with 99-test coverage. Fixed capture flow reliability, added re-injection guard for repeated captures, improved error messages, and validated all OCR pipelines. Tesseract offline mode now works fully CSP-compliant with locally bundled libraries.
  
  screenshot to text
  OCR extension
  image to text
  Claude Vision
  copy text from image
  text extractor
  screenshot OCR
  Tesseract
  offline OCR
  screen capture text

  SnapText — Screenshot to Text
  
  Stop retyping what's already on your screen.
  
  SnapText lets you drag a selection over any part of any webpage — a table, a code block, a scanned image (including from video), a UI screenshot, a PDF preview — and instantly extracts every word from it. No copy-pasting. No manual transcription. Just select and read.
  
  ── How it works ──────────────────────────
  
  1. Click the SnapText icon in your toolbar
  2. Click "Capture Region" — your popup closes and a crosshair appears
  3. Drag to select any area on the page
  4. Text is extracted and copied to your clipboard automatically
  
  That's it. No forms. No upload dialogs. No waiting.
  
  ── Two OCR engines. You choose. ──────────
  
  ▸ Claude Vision (recommended)
     Powered by Anthropic's Claude — the most accurate OCR available. Handles complex layouts, mixed fonts, handwriting, math, tables, and code. Requires a free Anthropic API key.
  
  ▸ SnapText OCR (offline mode)
     Runs entirely inside your browser. No internet required after the first load. No API key. Great for privacy-sensitive content or when you're offline.
  
  ── What it's great for ───────────────────
  
  ✓ Copy text from images and screenshots
  ✓ Extract data from tables and charts
  ✓ Grab code from screencasts or tutorials
  ✓ Read locked PDFs displayed in the browser
  ✓ Transcribe handwritten notes
  ✓ Pull contact info from photos
  ✓ Digitize scanned documents
  ✓ Capture text from videos (pause and capture)
  
  ── Privacy first ──────────────────────────
  
  Your API key is stored locally in your browser and never leaves your device except when making a direct call to Anthropic's API. No analytics. No tracking. No servers in between. History is stored locally and you can clear it anytime.
  
  ── No subscription. No account. ───────────
  
  SnapText is free to use with SnapText OCR (offline mode) right away. For Claude Vision, you only need a free Anthropic API key — pay only for what you use, at Anthropic's standard rates (typically fractions of a cent per capture).
  
  Get your free API key at console.anthropic.com
  
  ────────────────────────────────────────
  
  Try it on any page in 30 seconds. Click "Add to Chrome" to get started.
  
  What's new?
  v1.1.1
  —  Add multiple language text extraction support 
  —  Set SnapText OCR offline as default model to extract text from image
  — Resolve bug on capture region and set multiple drawer for capture
  
  v1.1.0 
  — Complete rewrite with 99-test coverage. 
  —  Fixed capture flow reliability, added re-injection guard for repeated captures, improved error messages, and validated all OCR pipelines. 
  — SnapText OCR - offline mode now works fully CSP-compliant with locally bundled libraries.
  
  Keywords:
  screenshot to text, OCR extension, image to text, Claude Vision, copy text from image, text extractor, screenshot OCR, SnapText offline OCR, screen capture text

• May 5, 2026
  short_description

  Capture any region of your screen and instantly extract text using Claude Vision AI or offline Tesseract OCR.

  Capture any region of your screen(image/video) and instantly extract text using Claude Vision AI or offline SnapText OCR model.

Permissions & access

Permissions

activeTabscriptingstoragetabs

Host access

<all_urls>

Screenshots