- What Clipverb collects
- Nothing, and the reason is structural rather than a promise: Clipverb has no backend, no account, no login and no telemetry, because it has no server at all. What exists on your own machine is a small settings file, a queue file, and your API key, which is held in the operating system's credential store rather than in either file.
- Where processing happens
- Everything happens on your machine, with one exception, and the exception is the point of the product. Captions are fetched to your machine and the note is written on your machine. The transcript text is sent to the AI provider you chose, with your own key on your own account, because that is what distillation is. Clipverb is not a party to it: no server of ours sits between the two, and the key never leaves the credential store except to be put on that one request.
- What leaves your machine
- Three things, and this is the complete list of what Clipverb's own code asks for. A request to the video site the link points to, to get the caption track and then the captions themselves. The transcript, to exactly one AI provider - the one you selected - and to no other. And a connection to your own machine at the loopback address, which is the optional browser helper talking to the app and never leaves the computer. There is no telemetry, no crash reporter, no update check and no licence call. This is enumerated from the source rather than measured: this product's outbound traffic has not been watched, and it makes no claim about Microsoft's WebView2, the component that draws the window.
- Effective date
- 2026-08-31(provisional while the product is in development; confirmed at its Store release)