Voice to text in Microsoft Teams

Does Teams have built-in voice-to-text?

For composing a chat message, no. Teams has no feature that turns your speech into typed text in the message box. I clicked through the formatting toolbar, the three-dot overflow, the per-message options, looking for a microphone that types. There isn't one. You can record and send a voice memo, but that's an audio clip your coworker has to press play on, not a typed message. Same with the meeting tools, which we'll get to, because they're the thing people keep mistaking for dictation.

Microsoft's own Q&A has people asking this exact question, and the honest answer there is the same: there's no native chat dictation on the desktop, and the usual workaround is Windows' built-in voice typing (Windows logo key + H) or a browser extension. That tells you something. When the most common answer to "how do I dictate in this app" is "use a tool outside the app," the feature isn't hiding in a submenu. It's just not there.

So if you want your voice to become a typed Teams message, the thing that does it lives outside Teams: your operating system, or a dedicated dictation app. Both are below. The meeting transcriber, the tool people most often confuse for this, is a third option, and it solves a different problem entirely. We'll get to all three.

Meeting transcription is not dictation

This is the part the cheerful guides blur, so let me be blunt about it. Teams transcription, live captions, the searchable transcript saved next to a recording, all of that listens to a meeting and writes down what everyone said. It is excellent at that. Microsoft documents it across meetings, webinars, and town halls, in dozens of languages, with speaker attribution. If your goal is "caption the call" or "get a record of who said what," Teams already does it, and so do tools like Tactiq built on top of it. None of that is what most people mean by voice-to-text.

Dictation is the opposite direction of effort. You are the only speaker, you are typing on purpose, and you want your own words to land in the compose box as text you can edit and send. A meeting transcript writes down a conversation after the fact. Dictation composes a message in the moment. They're as different as a court stenographer and a typewriter. Teams ships the stenographer. For the typewriter, you bring your own.

The fastest way: a system-wide hotkey

Here's where a dedicated app changes the math. Whisper by Remskill is not a Teams add-in, a meeting bot, or a browser extension. It's a desktop app that works like a keyboard: press a hotkey, speak, and the transcript is pasted at the cursor, in any app, the Teams compose box included. It works the same in the Teams desktop app and in Teams open in a browser, because as far as your computer is concerned, you're just typing.

Setup is short:

That's the whole loop. The transcript appears in the compose box, you read it, you press Enter.

Speak, and the message appears in Teams

Once it's running, the experience is unremarkable in the best way. You put your cursor in the channel or the chat, hold the key, talk, let go. A second or so later the text is sitting in the Teams compose box as if you'd typed it. No copy-paste, no separate window to fish the text out of, no voice memo for your coworker to scrub through at their desk.

Because the local transcription runs on your machine (pure-Rust, no Python sidecar, no server in the loop), it works offline. That matters more than it sounds for a work tool. The reply you're dictating, the half-formed thought about the release, the message to the manager you'd rather phrase carefully, none of it leaves your laptop on the way to becoming text. Windows' own built-in voice typing needs an internet connection to work at all; Whisper's local mode does not.

What the full Whisper app looks like

The hotkey is the part you'll use most, but there's a settings surface behind it. You pick your transcription engine: Whisper models, whose multilingual variants cover 99 languages and the English-only .en builds cover exactly one, or NVIDIA's Parakeet, about 600 MB, 5 to 10 times faster than Whisper on CPU, covering English plus 24 European languages. You set your hotkey, manage history, and save presets. None of that is required to dictate one Teams message. It's there when you want to tune.

Cleaning up dictated messages with AI

Spoken language is messy. You say "um," you restart sentences, you trail off into a noise that means "you know what I mean." Whisper has an optional AI enhancement step that trims filler and tidies the phrasing before it pastes. So "uh, yeah, so the, the deploy went out, I think we're, we're good" becomes "The deploy went out, I think we're good." On a work channel where the message is going to a manager or a client, that cleanup is usually worth it. On a quick reply in a side chat, you might just want the raw text.

That cleanup runs locally through Ollama, free, on your own machine. Pro users can route it through the cloud instead, but the filler-cleanup benefit doesn't require Pro; it's there in the free local pipeline. You can also just turn it off and paste the raw transcript, which for a fast "on my way" in a chat is often exactly right.

When to skip a dictation app and just use your OS

If you only need to dictate the occasional message, don't install anything. Your computer already does this for free. On Windows, press the Windows logo key + H and voice typing opens in any text box, the Teams chat bar included, with no subscription. On a Mac, the built-in Dictation shortcut (or the mic key) does the same, and on Apple silicon it runs on-device with no internet required. Both type straight into the Teams compose box, desktop app or browser, because they work at the OS level, not inside Teams.

The one tradeoff worth knowing: Windows' Win+H needs an internet connection to run, while macOS dictation and Whisper's local mode don't. For a quick "5 min late, starting without me" in a channel, the OS tool is the right call. Where a dedicated app pulls ahead is volume, the filler cleanup, and dictating offline: the longer and more often you do it, the more those matter.

Pick the smallest tool that solves your problem. For one message, that's the key you already have. For a morning of long replies, handover notes, and status updates across a dozen channels, the dedicated app stops feeling like overkill around the second or third paragraph you didn't have to type.

What Whisper costs

The local dictation pipeline, transcription and the AI cleanup over Ollama, is free for any signed-in user, with no card at signup. So getting your voice into Teams with Whisper costs nothing. Whisper Pro adds the cloud features (OpenAI transcription, cloud AI enhancement, voice web search), and it carries a separate trial. The exact numbers live on the pricing page rather than here, because prices move and a blog post is a bad place to keep them current.

Teams will probably ship real chat dictation eventually, the way apps tend to once enough people go looking for a microphone in the compose bar and find only a voice-memo button. Until then, your computer already has the feature, an app exists for when the built-in version isn't fast enough, and the meeting transcriber handles the wholly separate job of writing down a call. Three tools, three problems. Most of the time you need the smallest one.