Privacy Policy

Local-First Processing Philosophy

ScanTranslate is designed with your privacy as the top priority. We follow a local-first approach, which means:

• All OCR (Optical Character Recognition) processing happens directly in your browser using Tesseract.js
• Your images, PDFs, and documents never leave your device during OCR
• Translation history is stored only in your browser's IndexedDB
• You have complete control over your data

What Data is Collected?

Default: None. We do not collect any personal information by default. Specifically:

• No registration or account required
• No cookies tracking your behavior
• No analytics collecting your usage patterns
• No personal information stored on our servers

Where Does Your Data Live?

All your data is stored exclusively in your browser using IndexedDB:

• Translation history (last 30 translations)
• Language preferences
• Offline language packs (if downloaded)

Important: This data never leaves your device. If you clear your browser data, your history will be deleted.

Data Retention Policy

User-controlled. You have complete control over your data:

• Delete individual translations from your history anytime
• Clear all history with one click
• History is automatically limited to the last 30 translations
• Clearing browser data removes all stored information

AI Translation Service

For text translation, we use Vercel AI Gateway with the OpenAI GPT model:

• Provider: Vercel AI Gateway (OpenAI GPT-5-nano)
• Data sent: Only the extracted text for translation (not images or PDFs)
• Purpose: Text translation only
• Retention: API requests are not stored by us

The AI service receives only the text content for translation, never your images or documents.

Images, PDFs, and Documents

Never uploaded to servers. Your images, PDFs, and documents are:

• Processed entirely in your browser using Tesseract.js
• Never uploaded to our servers
• Never stored anywhere except your local device (if you choose to save them)
• Automatically deleted when you close the browser tab

Client-Side OCR with Tesseract.js

We use Tesseract.js, a pure JavaScript OCR engine that runs entirely in your browser:

• No server communication required for text detection
• Works completely offline (with offline language packs)
• All processing happens on your device
• No image data leaves your browser

Contact Information

If you have any questions about our privacy practices, please contact us at:

Email: privacy@pointtranslate.com

Changes to This Policy

We may update this privacy policy from time to time. We will notify you of any changes by posting the new policy on this page and updating the "Last updated" date.