Fact · Dictation software
0yes or no
DoNotType's README says audio and context go directly to the provider the user chose.
Quote found word for word on the live source, last checked October 22, 2026
In the source's own words
“Audio and context go directly to the provider you chose.”
DoNotType: README (GitHub), bojieli, GitHub (bojieli/DoNotType), 2026, How it works section, table, column 3 Transcribe.
Open the original- What it measures
- The README's table describing the transcription step.
- What it does not show
- The page does not describe on-device speech recognition. It also lists self-hosted vLLM or llama.cpp as provider options, so a user can run a model on their own server.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as DoNotType: speech on device: 0 1 = yes, 0 = no.
- App
- DoNotType by DoNotType
- Feature
- Speech processed on the device
- Detail
- Audio goes to the provider you choose
- As of
- 2026-10
- Note
- 0 means the maker's page says it does not.