Overview
At Whisper Web, we take your privacy seriously. Unlike traditional speech recognition services, Whisper Web processes all audio locally in your browser using WebAssembly and WebGPU technology. This means your audio files never leave your device, and we never have access to your recordings or transcriptions.
This Privacy Policy explains how we handle data, what limited information we may collect, and your rights regarding your personal information.
Information We Collect
Because all processing happens in your browser, we collect minimal information:
- Audio Files: Your audio files are processed entirely within your browser. They are never uploaded to our servers or any third-party servers.
- Usage Analytics: We may collect anonymized analytics data through Google Analytics, including page views, device type, browser type, and general location (country/city level). This helps us improve the service.
- Cookies: We use cookies for analytics and to remember your preferences (such as theme selection and language settings). See the Cookies section below for details.
How We Process Your Data
All audio transcription happens in your browser using the following process:
- You upload or record an audio file in your browser
- The Whisper AI model (running via WebAssembly) processes the audio locally
- The transcription text is displayed in your browser
- You can download the transcription or copy it to your clipboard
- All data remains on your device - nothing is sent to our servers
Important: Your audio files and transcriptions are stored temporarily in your browser's memory and are automatically cleared when you close the browser tab or refresh the page.
Third-Party Services
We use the following third-party services:
- Google Analytics: For anonymized website analytics and usage statistics. Google Privacy Policy
- Google AdSense: For displaying advertisements on our website. AdSense may use cookies to show relevant ads based on your browsing history. Learn more about Google Ads
- Hugging Face / Transformers.js: The AI models are loaded from Hugging Face's CDN. Model files are cached in your browser for faster loading on subsequent visits.
Note: These third-party services have their own privacy policies. None of these services have access to your audio files or transcription content.
Data Retention
Since all processing happens in your browser:
- Audio files and transcriptions are never stored on our servers
- All data exists only in your browser's memory during the session
- Data is automatically deleted when you close the tab, refresh the page, or clear your browser data
- Downloaded AI models are cached in your browser's storage for performance purposes and can be cleared at any time
Your Rights
Depending on your location, you may have the following rights:
- Right to Access: Request information about data we may have collected
- Right to Deletion: Request deletion of any analytics data associated with your browser
- Right to Opt-Out: Disable cookies and analytics tracking in your browser settings
- Right to Data Portability: Download your transcriptions directly from the browser interface
To exercise these rights, please contact us using the information in the Contact section below.
Security
Your data security is paramount:
- All processing happens in your browser - no audio data is transmitted over the network
- Our website is served over HTTPS to ensure secure communication
- We do not store, log, or have access to your audio files or transcriptions
- The AI models run in a sandboxed WebAssembly environment for additional security
Contact Us
If you have questions about this Privacy Policy or how we handle data, please contact us:
- Email: support@whisperweb.dev
- Contact Page: whisperweb.dev/contact
This Privacy Policy may be updated periodically. We will notify users of significant changes by updating the "Last Updated" date at the top of this page.