Fact · Dictation software
01 = yes, 0 = no
Whisper IME's readme says voice recognition works entirely offline once the models are downloaded, so recordings are not sent to a server for recognition.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Once the models are downloaded, voice recognition works entirely offline, ensuring your privacy and convenience.”
woheller69/whisperIME: Android Input Method Editor (IME) based on Whisper, woheller69, GitHub, n.d., Initial Setup section.
Open the original- What it measures
- The readme lists internet permission as needed only for the first model download, and gives no server or account for recognition.
- What it does not show
- The readme does not use the words 'audio' or 'servers'. The row reads 'entirely offline' as no audio leaving the phone.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as Whisper IME: audio off servers: 0 1 = yes, 0 = no.
- App
- Whisper IME
- Feature
- Keeps audio on the maker's servers
- Detail
- No server after model download
- As of
- 2026-10
- Note
- 0 means the maker's page says the app does not do this.