Last updated: October 26, 2026
LinguaSub ("we", "our", or "the extension") is a Chrome extension that provides real-time, on-device translated subtitles for web videos. This policy explains what data we access and how it is handled.
LinguaSub captures the audio stream of the active browser tab only when the user explicitly clicks "Start on this tab". This audio is used solely for on-device speech recognition and translation.
All processing — speech recognition (Whisper) and machine translation (NLLB) — runs entirely on the user's device inside the browser, using WebAssembly and WebGPU accelerated AI models.
We do not collect, store, transmit, or share any of the following:
Subtitle style preferences (font, color, position, etc.) and the selected
target language are stored locally in the browser via
chrome.storage.
This data never leaves the user's device.
On first launch, LinguaSub downloads AI model files (Whisper-tiny and NLLB-200) from Hugging Face. These files are cached in the browser's IndexedDB. No user data is transmitted during this download — only the model files are fetched.
| Permission | Purpose |
|---|---|
tabCapture | Capture the active tab's audio stream for on-device speech recognition. |
offscreen | Create an offscreen document to run the AudioContext and AI model worker (the service worker cannot use getUserMedia). |
storage | Save subtitle style settings and target language preference locally. |
activeTab | Obtain the active tab ID to route subtitle messages to the correct tab. |
<all_urls> | Inject the subtitle overlay content script on any page that plays video. |
LinguaSub is not directed to children under 13, and we do not knowingly collect personal information from children.
We may update this policy from time to time. Material changes will be reflected in the "Last updated" date above.
For privacy questions, please open an issue on the LinguaSub project page or contact the developer through the Chrome Web Store listing.