Voice to text in Discord

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

No, not the kind you mean. Discord has no feature that turns your speech into typed text in the message box. The closest-sounding thing is Text-to-Speech: type /tts followed by a message, or enable it in settings, and Discord reads that message aloud to everyone in the channel. That's text becoming speech. You're after speech becoming text. Same words, reversed arrow.

This trips people up constantly, and it's not their fault. "Text-to-speech" and "speech-to-text" are one swapped pair of words apart, and Discord only ships one of them. I clicked around the settings looking for the other one longer than I'd like to admit before accepting it wasn't hiding in a submenu. It isn't there.

So if you want your voice to become a typed Discord message, the tool that does it lives outside Discord: your OS, or a dedicated dictation app. Both are below. The thing that transcribes other people talking in a voice channel is a third option, and it's a different tool again. We'll get to all three.

Typing in every channel vs. just talking

The case for dictating into Discord 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, which matters when one of them is on a mouse or a controller. Across a busy evening of servers, the difference adds up.

The honest counterweight: a lot of Discord messages are three words long. "gg." "omw." "one sec." Dictation does nothing for those, you'd lose time switching modes. Voice typing earns its keep on the longer stuff: the raid plan, the bug report in a dev server, the paragraph you'd normally put off because typing it on a phone is a chore. That's the threshold. Short pings, keep typing. Anything past a sentence or two, talk.

The fastest way: a system-wide hotkey

Here's where a dedicated app changes the math. Whisper by Remskill is not a Discord bot, a server integration, 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 Discord chat box included. It works the same in the Discord desktop app and in Discord 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 Discord

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 Discord's message box as if you'd typed it. No copy-paste, no separate window to fish the text out of, no voice clip for your friends to scrub through.

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 Discord specifically. You're often in a voice channel already, on a connection you'd rather not load down further, and the audio for whatever you're dictating never leaves your laptop. 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 Discord 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 patch went live, I think we're, we're good" becomes "The patch went live, I think we're good." Whether that's worth it on Discord depends on the channel; a dev server, probably, a meme channel, probably not.

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 on Discord is often exactly the right call.

Transcribing a voice channel is a different job

This is the part the honest guides skip, so let me be blunt about it. Whisper turns your speech into a typed message. It does not transcribe a Discord voice channel, meaning it won't sit in a call and write down what everyone else is saying. That's a real thing people want, and it's a genuinely different tool: a Discord bot.

The bots built for this, Scripty being the most common, join a voice channel and post a running transcript of the conversation into a text channel. Scripty's core transcription is free, runs across roughly 55 languages, and processes audio without handing it to third parties. Others in this space include SeaVoice and DiscMeet. If your goal is "caption the whole call," reach for one of those, not Whisper. If your goal is "let me say my own message instead of typing it," that's Whisper, or your OS. Two different problems that happen to live in the same app.

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, Discord's 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. On your phone, the keyboard's microphone icon dictates straight into Discord's mobile message field; that's iOS or Gboard doing the work, not Discord, 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 "5 min late, starting without me," the OS tool is the right call. Where a dedicated app pulls ahead is volume, the filler cleanup, and dictating offline mid-call: 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 whole evening of long messages across five servers, 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 Discord 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.

Discord will probably ship real dictation eventually, the way apps tend to once enough people type /tts expecting it to do the other thing. Until then, your computer already has the feature, an app exists for when the built-in version isn't fast enough, and a bot exists for the wholly separate job of captioning a call. Three tools, three problems. Most of the time you need the smallest one.