Fact · Dictation software
11 = yes, 0 = no
SKI's home page says its speech recognition and neural voice both run on the user's device.
Quote found word for word on the live source, last checked October 22, 2026
In the source's own words
“Speech recognition and a natural neural voice, both running on-device.”
SKI home page and FAQ, SKI, SKI (heyski.io), 2026, Section 03, Private by design.
Open the original- What it measures
- Read on 2026-10-22 from the maker's home page.
- What it does not show
- The page does not name the speech model. Meeting audio sent through AgentCall is processed in the cloud, as the privacy policy states.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as SKI: speech on device: 1 1 = yes, 0 = no.
- App
- SKI
- Feature
- Speech processed on the device
- Detail
- Speech-to-text and voice run locally
- As of
- 2026-10
- Note
- 1 means the maker's page says the app does this