GitHub Copilot voice input
Copilot has voice in several places, and they aren't the same feature. VS Code has dictation and a spoken Voice Mode. Copilot CLI has its own /voice. In the JetBrains plugin we didn't find anything official. Here's how to start each, whether your audio stays on your Mac, and what to use where Copilot doesn't help.
Where each feature is
| Where | How to start | Where speech is recognized |
|---|---|---|
| VS Code chat dictation | Microphone button or ⌘I | On device on Apple silicon |
| VS Code editor dictation | ⌥⌘V | On device on Apple silicon |
| VS Code Voice Mode | Voice Mode button or ⇧⌘Space | Hosted, or OpenAI with your own key |
| Copilot CLI | /voice once, then hold Space | On your machine |
| VS Code for the Web | Microphone button | Microsoft's cloud voice service |
| JetBrains plugin | Nothing in GitHub's docs | – |
From code.visualstudio.com/docs/configure/accessibility/voice and docs.github.com, checked 6 November 2026.
VS Code
Dictation and Voice Mode do different things. Dictation puts your words in the input so you can edit them. Voice Mode is a spoken conversation, where the agent reads its answers aloud and listens for follow-ups. It's rolling out gradually, so it may not appear on your account yet. Dictation stops by itself after 20 minutes and keeps what it has so far.
There's a detail for private work. The audio stays on your Mac, but the dictation.experimental.llmCleanup setting sends the transcript text to a Copilot model by default. Turn it off if that matters. More in VS Code dictation on a Mac.
Copilot CLI
Enter /voice in a session and it downloads a voice runtime and a model. Hold Space for a short prompt, or press Ctrl+X then V to toggle recording for a long one. GitHub says transcription runs entirely on your machine and works on macOS on Apple silicon, but not on Intel Macs. It offers a fixed set of models: a multilingual default plus dedicated English and Spanish ones. /refine cleans up what you said afterwards, removing filler words and false starts.
JetBrains
GitHub's JetBrains docs cover chat, inline chat and suggestions without mentioning voice. JetBrains IDEs also have an integrated terminal, where Copilot CLI's voice input can work if the terminal meets the CLI's requirements. Dictation in IntelliJ, PyCharm and WebStorm covers the other options.
One key for everything
Each of these only works in its own tool, with its own shortcut. FnFlow is a free system-wide option for Mac: hold fn, talk and release, and the text goes into Copilot Chat, the terminal, a JetBrains tool window or a GitHub comment. It runs on your Mac and has a vocabulary for your project's names. It won't talk back like Voice Mode does.
Questions
How do I dictate to Copilot Chat in VS Code?
Click the microphone in the chat input or press ⌘I. Press and hold the shortcut for push-to-talk. The text goes into the input and isn't submitted.
Is Copilot voice input local?
Dictation on desktop VS Code and voice input in Copilot CLI both transcribe on your machine. VS Code's cleanup setting can still send the transcript text to a Copilot model, and hosted Voice Mode is a cloud feature.
Does Voice Mode work with Copilot Business?
Not the hosted version. VS Code's docs say it needs an eligible individual Copilot plan and isn't available with Copilot Business or Enterprise.
Does Copilot have voice input in IntelliJ?
GitHub's docs for the JetBrains plugin don't mention one. You can run Copilot CLI in the IDE's terminal and use its /voice, or use a system-wide dictation app.
Local Wispr Flow alternativeFnFlow vs VoiceInkVoice input for CursorHow 7 Mac dictation apps get you to your first dictationWhisper.cpp on Apple Silicon: which large-v3-turbo quantization to shipHow I built a local dictation appVoice dictation in Claude Code and the terminalWhy holding fn doesn't work for dictation on Mac (and how to fix it)How to run Whisper locally on an Apple Silicon MacSpokenly alternative for developersFnFlow vs EnviousWisprHow to dictate a good prompt for AI coding toolsVoice dictation in VS Code on a MacTeaching Whisper your jargon: initial prompt and replacementsWhy Whisper types "Thank you" on silence, and how to filter itPrivate dictation on a Mac at work: what actually leaves your machineVoice input for Codex CLI and the ChatGPT appVoice coding on a Mac: what actually worksWriting git commit messages by voiceDictating code review comments on GitHubDictation in IntelliJ IDEA, PyCharm and WebStorm on a MacDictation in Zed on a MacDictation in Terminal, iTerm2 and WarpWhich Whisper model to use on an Apple Silicon MacPush-to-talk dictation on a Mac: hold, toggle or streamSuperwhisper alternative for developersClaude Code voice mode: how to enable /voice and fix itWhisper apps: five ways to run Whisper locallyTalon voice coding vs a dictation appPush to talk on a MacDoes Claude have a voice mode?VoiceInk vs Wispr FlowVoiceInk vs SuperwhisperParakeet vs Whisper on a MacApple SpeechAnalyzer vs WhisperWhisper.cpp vs faster-whisper on a MacMlx-whisper vs whisper.cppGemini CLI voice inputVoice input in Google AntigravityVibe coding with voice input