Official documentation
Voice support in VS Code (accessibility voice documentation)
Visual Studio Code documentation (Microsoft), 2026
Read the originalRead on October 17, 2026
- What it is
- Microsoft's official VS Code page on voice. It covers built-in dictation in chat, the Agents window, editors and terminals, the on-device desktop model, the cloud path in VS Code for the Web, and the Voice Mode feature.
- How much weight it carries
- Official vendor documentation, read on 2026-10-17. The page marks built-in dictation as experimental, so its platform list and privacy wording may change.
Facts taken from this source
- To dictate a chat prompt in VS Code, select the microphone button in the chat input.
“To dictate a chat prompt, select the microphone button in the chat input” (Dictate in chat or the Agents window)
- In VS Code for the Web, dictation streams microphone audio to the Microsoft AI voice service for cloud transcription, because the on-device transcription is not supported there.
“In VS Code for the Web, where on-device transcription is not supported, dictation streams audio to the Microsoft AI voice service for cloud transcription.” (Use built-in dictation)
- In VS Code, built-in dictation inserts text in the chat input but does not submit the request.
“Dictation inserts text in the input but does not submit the request” (Dictate in chat or the Agents window)
- In a writable editor, VS Code's built-in dictation starts with the command Voice: Start Dictation in Editor.
“To dictate in a writable editor, run Voice: Start Dictation in Editor” (Dictate in an editor)
- Microsoft labels VS Code's built-in dictation as experimental, and says it might change or be removed.
“Built-in dictation is experimental and might change or be removed.” (Use built-in dictation)
- On a supported desktop platform, VS Code downloads a speech recognition model on first use, and after that speech recognition works locally and offline.
“On first use on a supported desktop platform, VS Code downloads the default nemotron-3.5-asr-streaming-0.6b speech recognition model. After the download completes, speech recognition works locally and offline” (Use built-in dictation)
- VS Code's built-in dictation is not available on Intel-based Mac computers, so those users need the VS Code Speech extension instead.
“Built-in dictation is not available on these desktop platforms: Intel-based Mac computers.” (VS Code Speech extension)
- 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.
“On desktop, dictation uses an on-device speech recognition model by default, so you can dictate without sending audio to an online service.” (Use built-in dictation)
- At a terminal prompt, VS Code's built-in dictation starts with the command Voice: Start Dictation in Terminal, run from the Command Palette.
“To dictate at a terminal prompt, run Voice: Start Dictation in Terminal from the Command Palette” (Dictate in a terminal)
- VS Code's built-in dictation converts speech to text in chat, the Agents window, editors and terminals.
“built-in dictation that converts your speech to text in chat, the Agents window, editors, and terminals” (Voice support (introduction))
- Visual Studio Code's voice documentation says its built-in dictation converts speech to text in chat, the Agents window, editors and terminals.
“Visual Studio Code supports spoken agent conversations with Voice Mode and built-in dictation that converts your speech to text in chat, the Agents window, editors, and terminals.” (Voice support)