Fact · Dictation in your apps
On the desktop, VS Code's built-in dictation uses an on-device speech recognition model by default, so dictation does not need to send audio to an online service.
Checked against its source on October 17, 2026
In the source's own words
“On desktop, dictation uses an on-device speech recognition model by default, so you can dictate without sending audio to an online service.”
Voice support in VS Code (accessibility voice documentation), Visual Studio Code documentation (Microsoft), 2026, Use built-in dictation.
Open the original- What it measures
- Microsoft describes built-in dictation in VS Code as experimental. The on-device model downloads on first use on supported desktop platforms.
- What it does not show
- Applies to the desktop app only. The page says the model downloads on first use, so the first run needs a network connection.