Fact · Dictation software
TypeLeast's home page says speech is recognized on the user's own computer, and that only text is sent to the model.
Quote found word for word on the live source, last checked October 25, 2026
In the source's own words
“语音在你的电脑上识别。发给模型的，只有文字。”
TypeLeast: home page (说出来，就写好了), TypeLeast, 2026, Privacy section of the home page.
Open the original- What it measures
- The privacy section lists the local speech models the app offers. It also says the first run downloads one speech model of about 241 MB.
- What it does not show
- The page does not say whether dictation works without a connection, so no offline row is written from this sentence.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as TypeLeast, speech on device: 1 1 = yes, 0 = no.
- App
- TypeLeast
- Feature
- Speech processed on the device
- Detail
- Recognized on your computer
- As of
- 2026-10
- Note
- 1 means the maker's page says the app does this.