Your audio stays on-device by default
Remote Compute is off by default and sends audio only to a user-paired device running OpenASR Server.
OpenASR Privacy
Your voice, your hardware.
OpenASR transcribes on your own machine. This page lists every network connection the CLI, server, and desktop app make — there is nothing beyond what's below.
The short version
Powerful transcription. Without handing over your voice.
OpenASR does not phone home. There is no telemetry, no analytics SDK, no account, and no cloud transcription path. Audio stays on the device unless you explicitly enable Remote Compute. If you choose online text refinement or translation, only the recognized text—not the audio—is sent to the provider you selected.
Audio, models, and results stay on-device in normal operation
Works offline, too
Transcription doesn't depend on any cloud service.
No uploads, no tracking, no sign-in
What OpenASR does not do
Privacy protections, built into every transcription.
What does reach the network, and when
When OpenASR connects, it tells you why.
A few optional features need a network connection. None of them silently uploads your audio for transcription.
$ openasr doctor --privacy
- audionative runtime
- transcriptlocal file
- telemetrydisabled
- cloud uploadnone
4 / 4 checks passed0 bytes left this device
Verify it yourself
A promise you can inspect.
These aren't just claims: the code that decides what touches the network is part of the Apache-2.0 open core. Read the model-pull path, the server's transcription route, and the catalog verification logic directly — nothing here depends on taking our word for it.
View the open core ↗Questions or something look off? Open an issue on GitHub