Privacy Policy

When you dictate, OmniVox captures audio from your microphone and processes it locally: Whisper transcribes the speech and Qwen structures it into a prompt, both running on your own CPU/GPU. This all happens offline — you can air-gap your laptop and OmniVox still works.

Your audio and transcripts are held only in memory long enough to produce the result, then discarded. OmniVox does not upload your voice or text anywhere, does not phone home, and includes no analytics, crash reporting, or usage tracking. Any settings, vocabulary, or history the app keeps are stored locally on your device and never synced to us.

tryomnivox.comis a static marketing site. It sets no cookies and runs no analytics, tracking pixels, or third-party scripts. We don't build profiles, and there's nothing to opt out of.

The site is hosted on Vercel. As with any web host, Vercel may process standard server request data (such as your IP address and browser user-agent) to deliver pages and protect against abuse. That data is handled under Vercel's privacy policy; we don't collect or retain it ourselves.

The install command (irm tryomnivox.com/install.ps1 | iex) and any download links fetch the OmniVox installer from GitHub Releases. Requesting those files is a normal connection to GitHub and is subject to GitHub's privacy statement. We don't receive any information about who downloads OmniVox.

OmniVox is a general-purpose developer tool and is not directed at children. Because we collect no personal data, none is knowingly collected from anyone, including children.

If this policy ever changes, we'll update this page and the date above. Since OmniVox is local-first by design, any change here will still start from the same principle: your words stay on your machine.

Questions about privacy? Open an issue on GitHuband we'll respond there.