Fact · Dictation software
11 = yes, 0 = no
ChordVox's privacy policy says local speech-to-text is performed on the user's device with built-in model families.
Quote found word for word on the live source, last checked October 20, 2026
In the source's own words
“Local speech-to-text processing is performed on your device using built-in model families such as Paraformer, Parakeet, and Whisper/GGML.”
ChordVox privacy policy, ChordVox, 2026, Section 2, 'What We Do Not Collect by Default', Audio recordings.
Open the original- What it measures
- The policy describes the local path as the default way speech is recognized.
- What it does not show
- Cloud transcription is an option. The policy says that when it is chosen, the recorded audio goes to the configured cloud service.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as ChordVox: on-device speech: 1 1 = yes, 0 = no.
- App
- ChordVox
- Feature
- Speech processed on the device
- Detail
- Local models; cloud optional
- As of
- 2026-10
- Note
- 1 means the maker's page says the app does this.