Dictation software for RSI

Typing less when typing hurts

I'll say the disclaimer once more, plainly, because it matters: this is not medical advice. RSI and carpal tunnel need a real diagnosis from a clinician, and the treatment is theirs to prescribe, not mine. Dictation software does not heal anything. What it does is reduce the number of keystrokes you make in a day, which is why a lot of people reach for it when their hands need a rest.

That framing is the honest one. Most of the advice you'll find online drapes a medical promise over a typing tool. I'd rather just describe the mechanism. You speak, the computer types. The keys you would have pressed, you don't. For an inbox you'd normally answer over forty minutes of typing, that's a few hundred keystrokes you simply skip.

Speaking runs about 145 words per minute for most people. Typing is closer to 40. So beyond resting your hands, you're also moving roughly three and a half times faster, which is a nice side effect when the slow, painful option was the only one you had.

What you can hand off to your voice

Almost all of it, honestly. Email is the big one: replies, follow-ups, the long apologetic one you've been avoiding. Documents and reports, where you'd rather think out loud than fight the cursor. Chat and messages across Slack, Teams, Discord, whatever your team lives in. Notes, both the meeting kind and the 11pm reminder kind. If it's text going into a box, you can say it instead of typing it.

What dictation won't do is run your computer for you. It puts words where your cursor is; it doesn't move the cursor, click menus, or navigate windows by voice. For most people, the bulk of the keyboard pain is the text, not the navigation, so handing off the text already moves the needle a lot. If your hands need more than that, there's a section below for exactly that case, and I point you at the right tools.

The fastest way: a system-wide hotkey

Here's where a dedicated app changes things. Whisper by Remskill is a desktop app that works like a keyboard: press a hotkey, speak, and the transcript is pasted at the cursor, in any app. Not a browser extension, not a single-app plugin. It's the same in your email client, your editor, your chat app, your notes — because as far as your computer is concerned, you're just typing.

Setup is short:

That's the whole loop. The transcript appears where your cursor was, you read it, you move on. The point worth dwelling on for sore hands: tap-to-toggle means you can start a dictation with a single key and never hold anything down.

Speak, and it types for you

Once it's running, the experience is unremarkable in the best way. You put your cursor where the text should go, start recording, talk, stop. A second or so later the text is sitting there as if you'd typed it. No copy-paste, no separate window to fish the words out of.

Because the local transcription runs on your machine (pure-Rust, no Python sidecar, no server in the loop), it works offline. For RSI use that's a quiet benefit. The email to your doctor, the insurance form, the work you'd rather not send to a vendor's logs: none of it leaves your laptop. Your computer already has a microphone and a CPU; for one paragraph it doesn't need a server in the loop.

AI cleanup so you're not fixing it by hand

This one matters more for sore hands than it first looks. Spoken language is messy. You say "um," you restart sentences, you trail off. If you then have to go back and fix all that by typing, you've put the keystrokes right back. So Whisper has an optional AI step that trims filler and tidies phrasing before it pastes. "Uh, yeah, so the, the report's basically done, I think" becomes "The report is basically done, I think." Fewer corrections means fewer keys.

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 turn it off and paste the raw transcript when you don't care about polish.

When you need full hands-free control

Here's the honest limit, because pretending otherwise would be doing you a disservice. Whisper reduces your typing load. It does not let you drive the whole computer by voice. If your hands need a real rest from everything (mouse, keyboard, navigation, not just the text) you need a tool built for that, and I'd point you to one of two.

Dragon Professional (Windows) is the long-standing option for full voice control. Beyond dictating text, it lets you move and click the mouse, launch apps, navigate menus, and run custom voice commands like "move mouse lower left," "open Word," "bold that." It's a paid, heavier piece of software, and it's the most complete dictation-plus-commands package most people will find.

Talon Voice (macOS, Windows, Linux) goes further into accessibility. It pairs voice commands with eye tracking and noise-based clicking, so you can control the cursor and click without your hands at all, and script the whole thing in Python to fit your workflow. It has a steeper learning curve, but for fully hands-free computer use it's in a different class than a dictation tool. If that's what your hands need, start there, not here.

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 the hotkey, choose push-to-hold or tap-to-toggle, manage history, and save presets. None of it is required to dictate one email. It's there when you want to tune.

Free built-ins to start with

If you only need to dictate the occasional message, don't install anything yet. Your computer already does this for free. On Windows, press the Windows logo key + H and voice typing opens in any text box, no subscription. On a Mac, the built-in Dictation shortcut does the same, and on Apple silicon it runs on-device with no internet required. Try the free built-in first; if your hands need it more often, a dedicated app pulls ahead.

Where a dedicated app earns its place is volume and friction: the filler cleanup, tap-to-toggle so you never hold a key, dictating offline, and the same hotkey working identically across every app. The longer and more often you lean on dictation to spare your hands, the more those small things add up. For one note a week, the built-in is plenty.

Pick the smallest tool that solves your problem. For one message, that's the key you already have. For a workday of email and docs you'd rather not type, 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 any app with Whisper costs nothing. Whisper Pro adds the cloud features (OpenAI transcription, cloud AI enhancement, voice web search), and it carries a separate trial that asks for a card. 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.

If your hands hurt, the first appointment is with a clinician, not a download page. But once you've got that sorted, the boring, useful truth holds: the fastest way to stop a keyboard from hurting is to press it less. Dictation does that for the text. For the rest of the computer, Dragon and Talon exist. Pick the smallest tool that gives your hands the break they're asking for.