TL;DR: There are two serious ways to control your Mac with your voice in 2026. Apple's built-in Voice Control is free, on-device, and accessibility-grade: enable it in System Settings → Accessibility → Voice Control. Infina ($8.25 a month, billed annually at $99, unlimited words and voice commands) is built for speed: open and switch apps, control system settings, and dictate and send AI prompts entirely hands-free. If you prompt AI tools all day, Infina turns typing from your bottleneck into a voice loop; this guide covers both options with setup steps.
The short version, if you only read one paragraph on this page. Infina runs on three spoken triggers and there is no fourth. Say "type" and a sentence and it lands as typed text in whatever app is in front of you. Say "send it", or just "enter", and it presses Enter so the prompt actually goes. Say "open Cursor" or "open Slack" and your computer switches apps for you.
Nothing is held down and nothing is pressed. There is no push-to-talk key to find and no Enter key to reach for two hundred times a day, which is the part every other tool in this category leaves to your hands. Talon is the other genuinely hands-free option and it is free, but it asks you to learn a command language. Three ordinary words is the whole difference.
Option 1: Control your Mac with your voice for free (Apple Voice Control)
Voice Control is Apple's accessibility-grade voice command system, built into macOS. Per Apple's documentation, it requires internet only for a one-time file download when first enabled.
After that it works fully offline. Apple's Voice Control support article states that audio is processed on your device, keeping your data private.
How to enable Voice Control
- Open the Apple menu → System Settings.
- Click Accessibility in the sidebar.
- Click Voice Control.
- Turn on Voice Control. The first time, your Mac must be connected to the internet to complete a one-time file download from Apple.
- When the microphone indicator appears, just speak. Try "Open Mail" or "Show numbers."
That's it. No account, no payment, no third-party install.
What Voice Control is great at
- Operating literally everything. Say "Show numbers" and every clickable item on screen gets a number; say the number to click it. "Show grid" overlays a numbered grid for clicking anywhere, even in apps with unlabeled buttons.
- Navigation and system commands: "Open Mail," "Scroll down," and dozens more. Say "Show commands" to see everything available in context.
- Dictation and editing: switch to dictation mode, enter text word-by-word or even character-by-character, and run formatting commands on selected text.
- Free, private, always available. It ships with macOS, runs on-device, and works with VoiceOver for full accessibility workflows.
If you have a motor impairment, RSI, or an injury, stop reading here and go set it up. It is the most complete voice control system on any desktop OS, and no paid app (ours included) replaces it for full accessibility use.
Where Voice Control gets clunky for productivity
Voice Control is designed so that everything is possible by voice. That completeness has a cost when you just want to work fast:
- It's always-on and literal. It listens to everything you say while enabled, and stray speech can trigger commands. Note also that while Voice Control is on, standard macOS Dictation isn't available; Voice Control's own dictation mode takes over.
- Multi-step actions stay multi-step. Clicking by numbers or grid coordinates is empowering when you need it and slow when you don't. "Show numbers... 14... Show numbers... 7" is not a flow state.
- Dictation is the weakest part for prose and prompts. It's built for command accuracy, not fast free-form transcription into whatever app you're driving.
- No concept of a "send" workflow. It can type text, but stringing together dictate, submit, switch window, dictate again means narrating every micro-step yourself.
None of this is a flaw. It is the right design for its mission, but it is why a second category of tool exists.
Option 2: Infina, voice control built for productivity
Infina ($8.25 a month, billed annually at $99, on Mac and Windows) doesn't try to control everything. It covers the specific loop that keyboard-heavy workers, especially people prompting AI tools like Claude Code and Cursor all day, actually repeat hundreds of times:
- Open and switch apps by voice; switch browser tabs.
- Control the system: volume, brightness, media playback, Do Not Disturb, dark mode, screenshots.
- Dictate AND send. This is the wedge. Dictation apps still make you touch the keyboard to trigger and send; Infina completes the whole prompt, send, switch-app loop hands-free. You speak a prompt, say "send," and it types it and hits Enter, then switches you to the next app on command. More on that workflow in hands-free voice prompting.
That loop is the productivity story. You can speak thousands of words of prompts a day, keep several AI agents busy at once, and never touch the keyboard between them.
The controls in 20 seconds
| You want to... | Do this |
|---|---|
| Dictate text | Hold Option (⌥), speak, release |
| Speak one command (push-to-talk) | Hold fn, say "open Terminal," release |
| Go fully hands-free | Double-tap Cmd (⌘) to toggle hands-free mode |
| Type hands-free (hands-free on) | Say "type" plus your words, then "send it" to send |
| Wake for one command by key | Double-tap Ctrl (while hands-free is on) |
Hands-free listening runs on-device, and transcription is on-device by default too. Nothing is recorded or sent while it waits for you to speak.
Infina's honest limits
- Mac and Windows, no phone app (Apple Silicon is needed for the Mac's on-device models). Two of the commands on this page, reading your screen and driving a page inside your browser, are Mac-only; Infina for Windows sets out what a PC does instead.
- $8.25 a month, billed annually at $99. A Free plan of 2,000 free words comes first, no card required, and there's a 7-day no-questions refund after that. How the pricing works: flat, unlimited words and commands, no per-seat or per-minute charge.
- English-only base product; more languages require the optional $5/month cloud add-on (billed annually at $60).
- Hands-free mode is off by default and labeled experimental. Push-to-talk is the mature path; hands-free is the newest surface.
- It is not an accessibility tool. It won't click arbitrary buttons by number or drive every UI. Apple's Voice Control does that, free.
Which one should you use?
- Accessibility need (motor impairment, RSI flare, injury): Apple Voice Control. It's the real thing, and it's free.
- Occasional convenience ("open Mail," click without hands): Voice Control again. Start free; you may never need more.
- You prompt AI tools all day and want to speak, send, and switch apps without touching the keyboard: that's the job Infina was built for. See how it compares to dictation-only tools in Wispr Flow vs Infina.
- You mostly want dictation, not control: a dictation-first app is the better fit; voice control is Infina's differentiator, not its only mode.
FAQ
Can I control my Mac with my voice for free? Yes. Apple's Voice Control is built into macOS: System Settings → Accessibility → Voice Control. After a one-time download it works offline, processes audio on-device, and can operate essentially everything on screen.
What voice commands does macOS Voice Control understand? Navigation ("Open Mail," "Scroll down"), item clicking ("Show numbers," "Show grid"), dictation and text editing, and more. Say "Show commands" while it's on to see every available command in context.
Does Apple Voice Control send my voice to Apple's servers? Per Apple's Voice Control support documentation, audio is processed on your device. It needs internet only for the one-time file download when you first enable it.
What does Infina do that Apple's Voice Control doesn't? A fast productivity loop: say "type" plus your prompt, say "send it" to actually submit it, then switch apps or tabs by voice. Add quick system controls (volume, media, dark mode, screenshots), and hands-free mode works from across the room with no keys at all. Voice Control can do many individual steps, but not as one fluid hands-free flow.
Can I use voice control while dictating normally on my Mac? One catch from Apple's docs: while Voice Control is on, standard macOS Dictation isn't available. Voice Control's own dictation mode replaces it. Infina takes a different approach: dictation and commands are separate triggers (hold Option vs hold fn), so they don't fight.
Does controlling a Mac by voice work offline? Apple's Voice Control does after the initial download. Infina's default mode does too: listening and transcription run on-device, and only its optional cloud add-on needs a connection.
The bottom line
Learning how to control your Mac with your voice starts free: turn on Apple's Voice Control and you can operate the entire machine on-device, today. If that covers you, wonderful. Bookmark this and pay nobody. We compare the free built-in dictation side of this in Apple Dictation vs Infina, and if you want to control everything by voice, including writing code word by word, the deep end of that pool is covered in Talon vs Infina.
If you live in AI tools and what you actually want is to speak prompts, send them, and switch apps without your hands, that's the narrower, deeper job Infina does. It's $8.25 a month, billed annually at $99, for unlimited words and voice commands, and you can try it risk-free for 7 days with our no-questions money-back guarantee.
Which app to do this with
The steps above work with any of these. They stop being equal the moment you want the keyboard out of the loop.
The tools this page covers (Wispr Flow, Talon, Apple Dictation) are at the top. The rest of the field follows, because the right answer is sometimes none of the above.
| Tool | Price | Keyboard needed | Pick it if |
|---|---|---|---|
| Infina | $8.25 a month, billed annually at $99, unlimited words and unlimited commands | No. Speak "type", speak the prompt, say "send it" or "enter". | you want to prompt AI tools without touching the keyboard. Say "type" and the words go in, "send it" and the prompt goes, "open Cursor" and you are in the next agent. It is the only one of these that finishes the whole loop by voice in the tools developers prompt in all day. |
| Wispr Flow | $15 a month, or $144 a year billed annually | Yes. A key to start dictating, Enter to send. | you need dictation on an iPhone or an Android phone as well as a laptop, or you write in one of 100+ languages. Those are the two things Infina does not ship. |
| Talon | free | No, once you have learned its command language. | you want to drive the entire computer by voice, cursor and clicks included, and you are willing to learn a command language to get there. Talon is the serious hands-free tool on this list. Infina goes after the same freedom with three ordinary English words instead of a syntax to learn. |
| Apple Dictation | free, built in | Yes. A key to start dictating, Enter to send. | you dictate a sentence here and there and do not want to install anything. |
| Superwhisper | $8.49 a month, $84.99 a year, or $249.99 once | Yes. A key to start dictating, Enter to send. | you want to pick and swap the speech model yourself, and dictation into a text box is the whole job. It stops where the text box ends: there is no spoken send, and no spoken app switch. |
| MacWhisper | 65 euros, paid once | Yes. A key to start dictating, Enter to send. | the job is transcribing recorded audio files rather than talking to your computer while you work. |
| VoiceInk | $25 to $49, paid once | Yes. A key to start dictating, Enter to send. | you want plain local dictation at the smallest possible price and you never need your voice to control the machine. |
The part that is actually different: zero keypresses
The mainstream dictation apps (Wispr Flow, Superwhisper, MacWhisper, VoiceInk, Apple Dictation) are all push-to-talk: you hold or press a key to start talking, and you press Enter to send. That is two physical acts on every single prompt. A hundred prompts in a day is two hundred keypresses that exist only to start and stop the tool. Infina removes both of them. Nothing is held, nothing is pressed, and the same loop runs on three spoken words.
There are three triggers and there is no fourth. "type" types, "send it" sends, "open" opens and switches apps. The send trigger answers to either wording, "send it" or a plain "enter", whichever you find yourself saying. That is the entire vocabulary: no command language, no grammar, no custom scripts to write, nothing to memorize beyond those three words.
When Infina is not the answer. If you need dictation on an iPhone, an iPad, an Android phone or Linux, Infina is a Mac and Windows desktop app and there is no phone version. Wispr Flow covers phones.
Everywhere else, the difference is the loop. Every other tool in that table types words into a box and stops, leaving your hands to press Enter and pick the next window. Infina finishes it: say "type" and your sentence, say "send it" (or just "enter"), say "open Cursor", and keep going without a key.