Fact · Dictation software
Whispering's README says it has no on-device transcription models, so speech is sent to a transcription endpoint.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“On-device transcription models. Transcription needs an endpoint.”
Whispering README (apps/whispering, Epicenter repository), Epicenter (EpicenterHQ), GitHub, 2026, What is not supported.
Open the original- What it measures
- The same README sentence as the offline fact, read for the speech-processing feature.
- What it does not show
- The endpoint can be a local server the user runs, which the README does not describe as part of the app.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as Whispering, speech on device: 0 1 = yes, 0 = no.
- App
- Whispering
- Feature
- Speech processed on the device
- Detail
- Transcription goes to an endpoint
- As of
- 2026-10
- Note
- 0 means the maker's page says it does not