Speech to text in Slack, honestly

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

No — not the kind you mean. Slack has no feature that turns your speech into typed text in the message box. What it has is the audio clip: click the microphone icon in a channel or DM and Slack records audio, up to five minutes, on every plan. That's a voice memo, not a dictated message.

Slack can transcribe that clip, but only when you ask. After recording, you click the "Generate transcript" icon, and a preview of the text appears below the clip. It is not automatic, despite what half the internet will tell you. So the clip transcript is the text of a recording you made, not the message you wanted to dictate and send as a normal Slack message. Different workflow, different result. I spent a genuinely embarrassing amount of time clicking that mic icon expecting words to appear before I accepted that they never would.

If you want your voice to become a typed Slack message, the tool that does it lives outside Slack: your OS, or a dedicated dictation app. Both are below.

Typing in Slack all day vs. just talking

The case for dictating into Slack is simple. Speaking runs about 145 words per minute; typing for most people is closer to 40. That's roughly three and a half times faster, and it frees your hands. For a busy channel, the difference adds up across a day.

The honest counterweight: a lot of Slack messages are six words long. "On it." "Looking now." "Can you share the link?" Dictation does nothing for those; you'd lose time switching modes. Voice typing earns its keep on the longer stuff: the status update, the handoff note, the reply you'd normally put off because typing it is a chore. That's the threshold. Short pings, keep typing. Anything past a sentence or two, talk.

The fastest way: a system-wide dictation hotkey

Here's where a dedicated app changes the math. Whisper by Remskill is not a Slack app, a 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, Slack's message box included. It works the same in the Slack desktop app and in Slack 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 press Enter.

Speak, and the message appears in Slack

Once it's running, the experience is unremarkable in the best way. You put your cursor in the channel, hold the key, talk, let go. A second or so later the text is sitting in Slack's message box as if you'd typed it. No copy-paste, no separate window to fish the text out of, no clip for your teammate to play back.

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. Slack's own clip transcription is cloud-processed, and Windows' built-in voice typing needs an internet connection to work at all. Whisper's local mode does not. The audio for that internal status update never leaves your laptop.

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 Slack message. It's there when you want to tune.

Cleaning up dictated Slack messages with AI

Spoken language is messy. You say "um," you restart sentences, you trail off. Whisper has an optional AI enhancement step that trims filler and tidies the phrasing into something you'd send to a colleague 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."

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. For Slack, where tone lives somewhere between email and texting, that "make it sound professional" pass is the feature people end up keeping.

Slack's own audio clips and huddles vs. real dictation

It's worth being precise about what Slack already does, so you don't go looking for a setting that isn't there. Audio clips: recorded media, up to five minutes, transcribable on demand. Huddles: live audio rooms for talking with teammates. Neither one turns your speech into a typed message you send and edit like text. They're good tools for "let me just say this out loud," and a poor substitute for "let me dictate this and hit send." If your goal was the second one, Slack was never going to give it to you. That's not a bug, it's a scope.

When to skip a dictation app and just use your OS

If you only need to dictate the occasional short 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, Slack 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. On your phone, the keyboard's microphone icon dictates straight into Slack's mobile message field; that's iOS or Gboard, not Slack, but it works.

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 "running five late," 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.

Call it the lunchbox test. On a Tuesday evening I'm making lunchboxes, sandwich, fruit, the yogurt the younger one will refuse, and a message needs to go out before everyone scatters. I grab the laptop one-handed, hit the hotkey, and dictate it between cucumber slices: stop to ask how to spell a name, the dictation waits, keep going. The message goes out. The lunchboxes get made. That exact moment used to be fifteen minutes of typing one-handed.

Once one hotkey follows your cursor everywhere, the same flow lets you dictate to ChatGPT — speak the prompt and it lands as clean text in the chat box, no retyping a long request by hand.

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 Slack 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.

Slack will probably ship real dictation eventually, like most apps do, once enough people click the mic icon expecting it. Until then, your computer already has the feature, and an app exists for when the built-in version isn't fast enough. Pick the smallest tool that solves your problem. For most short messages, that's the key you already have.