TL;DR: AI writes the code and the documents now; your remaining job is describing what you want, and typing caps that channel at a commonly cited 40 to 80 words per minute while speech runs 130 plus. Infina removes the cap and then the keyboard itself: from a couple of feet away, say "type" plus your prompt and it gets typed, say "send it" (or just "enter") and Enter is pressed, say "open Cursor" or "open Claude Code" and you are briefing the next agent, no key touched anywhere in the loop. Most dictation apps stop at typing; Infina runs that whole prompt, send, and switch-apps cycle hands-free in plain English, with no command language to learn. Voice typing with a key is free and unlimited; hands-free typing is $8.25 a month, billed annually at $99 (as of July 2026), unlimited hands-free words, on your computer by default, 7-day refund.
The bottleneck argument is arithmetic plus a job description, and both are laid out below for you to check.
The job changed underneath you
Five years ago, the limiting factor of knowledge work was production: writing the code, drafting the document, building the deck. Hands on keyboard was the work.
Now AI tools produce the artifact. Claude Code writes the migration, Cursor writes the component, a chatbot writes the first draft. What is left for the human is the part the AI cannot do: knowing what you want and describing it precisely.
That description is text. Lots of it. Context, constraints, examples, corrections, follow-ups. On a heavy day, a person directing AI tools produces thousands of words of pure instruction.
And nearly everyone still produces those words the slow way: typing them.
Why typing is the bottleneck
A bottleneck is the narrowest point in a pipeline. Walk the AI pipeline and look at the widths.
The AI generates faster than you can read. The terminal executes instantly. The one stage that crawls is you, pushing intent through your fingers.
The arithmetic is open; check it yourself. Commonly cited averages put typing near 40 words per minute, with practiced typists at 60 to 80. Conversational speech is commonly cited at 130 to 160 words per minute. Whatever exact numbers you use, the ratio lands around three to one. We compare the measurements in depth in dictation vs typing speed.
Now put a workload through it. Thirty prompts a day at 150 words each is 4,500 words of instruction:
- Typed at 60 words per minute: about 75 minutes.
- Spoken at 140 words per minute: about 32 minutes.
Same prompts, same intent, around 40 minutes of difference every single day. Over a working year that is well over 100 hours spent pushing words through the narrow pipe.
The hidden cost is worse than the visible one
The minutes are the measurable loss. The behavioral loss is bigger.
When words are expensive, you ration them. Typed prompts get compressed: context gets dropped, constraints get skipped, "you know what I mean" gets assumed. The AI does not know what you mean, so it guesses, and you pay in retry rounds.
When words are cheap, you spend them. Spoken prompts naturally carry more context because ten extra seconds of talking buys three extra sentences of specification. Better-specified prompts mean fewer round trips, which compounds on top of the raw speed gain. The full productivity picture, including where the gains are real and where they are hype, is in speaking vs typing productivity.
There is also a parallelism cost. If your hands are pinned to one keyboard writing one prompt, you run one agent at a time. People who direct several AI sessions at once, the workflow behind vibe coding by voice, need an input channel that moves at the speed of switching attention, not the speed of typing.
The counterarguments, taken honestly
The thesis has real objections. Here they are, without a strawman.
"Editing still needs a keyboard." True, and voice does not pretend otherwise. Renaming a variable, tweaking a line, navigating code: keyboard work, and it should stay keyboard work. But be honest about the split in an AI-era day: the bulk of your fresh word count is describing intent, not surgically editing. Voice takes the bulk; the keyboard keeps the scalpel. Nothing is taken away from you.
"I can't talk to my computer in an open-plan office." Also true. Dictating in shared space has a social cost, and hands-free operation from across the room wants a quiet-ish room besides. Voice input fits home offices, private offices, and remote work, which happens to be where much of AI-heavy work already lives. In a shared space, holding a key and talking at a normal speaking volume is viable; hands-free is for the room where you can think out loud.
"My typing is fast enough." Maybe. At 80 words per minute you are still under the commonly cited floor of conversational speech, and you are typing with your posture, wrists, and attention chained to the desk. The bottleneck is narrower for you, but it is still the narrowest stage in the pipeline.
"Dictation output is messy." Unedited dictation is, agreed. That is why, on a Mac, Infina's Tami 1 cleans it up on your computer: it removes filler words and stutters and fixes punctuation and capitals, while keeping your exact words instead of rewriting them. And for prompting, mess barely matters anyway: AI chat tools parse loose spoken phrasing effortlessly.
What removing the bottleneck looks like
Step one is dictation itself. Infina starts with dictation on your computer: hold fn (Right Alt on Windows), speak, release, and your words are typed into whatever app is focused. Transcription runs on your Mac's Neural Engine, works offline, Infina's Tami 1 tidies the text on your Mac, and by default no audio or transcripts are stored. It is free with no word limit, and that alone moves you from typing speed to speaking speed.
Step two is removing the hands entirely, because voice typing with a key still leaves a keyboard residue: a key held for every dictation and a key pressed for every send, hundreds of times a day.
Infina's hands-free mode (double-tap Cmd to toggle it on; it ships off by default and is labeled experimental) closes the loop:
- Say "type" plus your words: "type add retry logic to the upload endpoint and write a test for the timeout case." Infina types it. "Type" is the trigger; no hotkey exists in this loop.
- Say "send it". Enter is pressed.
- Say "open Claude Code", or "open Cursor", or "open Notes". The app switches.
- Repeat, from a couple of feet away, while the previous agent is still working.
That last detail is the point: the bottleneck is not just speed, it is serialization. When prompting, sending, and switching are all spoken, you brief agent two while agent one runs. Shipping speed follows prompt throughput, an argument we push further in prompt faster, ship faster.
Scope stated honestly: Mac and Windows with no phone app, Apple Silicon required on the Mac, English on your computer (Infina Unlimited adds an online option for 90+ languages), and hands-free is the experimental layer while voice typing with a key is the mature everyday path.
The economics of unblocking
Infina's voice typing with a key is free, tidy-up included, so step one costs nothing. Hands-free starts with 2,000 free hands-free words, no card required, then $8.25 a month, billed annually at $99 (as of July 2026), every update included, with unlimited hands-free words and nothing metered, plus a 7-day no-questions money-back guarantee. Details on pricing.
Run it against the arithmetic above. Hands-free typing at $8.25 a month on the yearly plan is under 40 cents a working day. If voice returns even 20 minutes a day, the year is paid for inside the first couple of weeks, and everything after that is kept time. That is the whole business case, and every number in it is yours to audit.
FAQ
What does "typing is the bottleneck" actually mean? In AI-era work, the AI produces the artifact and the human produces the description. Typing caps that description channel at a commonly cited 40 to 80 words per minute while speech runs 130 plus, making your keyboard the slowest stage in the pipeline.
Is speaking really three times faster than typing? The ratio comes from open arithmetic on commonly cited ranges: around 40 words per minute average typing (60 to 80 for practiced typists) versus 130 to 160 words per minute for conversational speech. Your personal ratio may be two-to-one or four-to-one; measure your own numbers against your own prompt log.
Doesn't coding still require typing? Editing code does, and voice should not replace that. The bottleneck claim is about fresh word production: prompts, instructions, and descriptions, which dominate an AI-heavy day and are faster spoken.
What about open-plan offices? Honest limit: dictation has a social cost in shared space, and hands-free wants a quiet-ish room. Voice input fits home and private offices best; holding a key and talking at normal speaking volume is the workable middle ground elsewhere.
Does Infina send my prompts to a server? Not by default. Transcription runs on your Mac's own chip, works offline, and no audio or transcripts are stored by default. The tidy-up, Infina's Tami 1, also runs on your Mac. Sending audio to a server is an optional switch on Infina Unlimited, off by default.
How much does Infina cost? Voice typing with a key is free, tidy-up included. Hands-free typing is $8.25 a month, billed annually at $99 (as of July 2026) with every update included, unlimited hands-free words, and a 7-day no-questions-asked refund.
The bottom line
The AI era moved the work from producing artifacts to describing them, and almost nobody upgraded the description channel. Typing is the bottleneck: the arithmetic is open, the daily cost is tens of minutes, and the hidden cost is compressed prompts and serialized agents.
The fix is not typing harder. It is speaking your instructions instead, and then taking your hands out of the loop entirely: type, send, open the next app, all by voice, from across the room.
Infina is the Mac app built to do exactly that: it runs on your Mac by default, holding a key and talking is free, and hands-free typing is $8.25 a month, billed annually at $99 (as of July 2026). If the bottleneck does not visibly open up in your first week, the refund is one email.
What to use, if you want to work this way
Arguments are cheap without a tool attached. Here is the field, and the reader each one fits.
None of these is the wrong answer for everybody. What differs is which reader each one is right for.
| Tool | Free with tidy-up, no word limit | Price | Keyboard needed | Pick it if |
|---|---|---|---|---|
| Infina | Yes: no word limit, no card, no API key (16 GB on Windows) | Hands-free typing: $8.25 a month, billed annually at $99. Voice typing with a key, tidy-up included: free, no word limit | No. Say "type", the prompt, then "send it". Holding a key instead is free. | 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 finishes the whole loop by voice in the tools developers prompt in all day, and holding a key instead gives you dictation that tidies up your words for free, with no word limit. |
| Wispr Flow | No: weekly-limit notice at 2,000 words, blocks new dictations above 5,000 | $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 want 100+ languages on a free plan. Infina has no phone app, and beyond English its 90+ languages are a paid-plan option. |
| Superwhisper | No: the tidy-up is paid | $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 engine 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 | No: the tidy-up needs Pro plus your own API key or a local AI | 64 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 | Paid, from $25 once; the GPL source is free to build | $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. |
| Talon | No: it does not tidy up your words | 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 | Partly: light cleanup on newer Macs only | 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. |
The first difference: zero keypresses
The mainstream dictation apps (Wispr Flow, Superwhisper, MacWhisper, VoiceInk, Apple Dictation) stop at typing: you hold or press a key to start talking, then press Enter to send and click over to the next app yourself. Infina is hands-free: nothing is held, nothing is pressed, and the whole loop runs on three spoken words. When you would rather hold a key, that works too, free with no word limit, with your words tidied up on your computer.
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. Hands-free typing is the paid part: 2,000 free hands-free words, then $8.25/month billed yearly ($99). Unlimited voice commands are free.
The second difference: holding a key is free
In Infina, holding a key and talking has no word limit and needs no card, with your words tidied up on your computer (16 GB on Windows). Most dictation apps cap free words or charge for the tidy-up. The key is fn on a Mac and Right Alt on Windows.
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. Most of the tools in that table stop at typing the words, 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.
Quick answers
Is there a free dictation app that tidies up your words, with no word limit? Yes: Infina. Holding a key (fn on a Mac, Right Alt on Windows) is free voice typing that tidies up your words on your computer: it types what you say into any app, with no word limit and no card (16 GB on Windows). Infina is hands-free voice for Mac and Windows: you talk, and it types, sends and opens apps. Most dictation apps cap free words or charge for the tidy-up.
What are the trigger words in Infina? Three. Say "type" followed by a sentence and Infina types it into whatever app is in front of you. Say "send it", or just "enter", and it presses Enter, so the prompt actually goes. Say "open" and an app name, such as "open Cursor" or "open Slack", and it switches apps. That is the whole hands-free loop, and none of it needs a key held down. If you would rather hold a key and talk, that is free, with no word limit.
Can I use Claude Code or Codex without touching the keyboard? Yes, with Infina running in hands-free mode. Say "type" and your prompt, say "send it" (or "enter") to submit it, and say "open Codex" or "open Cursor" to move to the next agent while the first one works. Most dictation apps stop at typing, so the send and the app switch stay with the keyboard.
Is there a dictation app that does not need a hotkey or a key held down? Infina, in hands-free mode. The mainstream dictation apps (Wispr Flow, Superwhisper, MacWhisper, VoiceInk, Apple Dictation) all need a key: you hold or press a key to start talking, then press Enter to send, which is two physical acts on every prompt. Infina removes both. Say "type" and your sentence, say "send it" or "enter", say "open Cursor". Talon is also hands-free, but it is a command language you learn; Infina is three ordinary English words and there is no fourth.
Is Wispr Flow or Infina better? Pick Wispr Flow if you need dictation on an iPhone or an Android phone as well as a laptop, or you want 100+ languages on a free plan. Infina has no phone app, and beyond English its 90+ languages are a paid-plan option. Pick Infina if 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 finishes the whole loop by voice in the tools developers prompt in all day, and holding a key instead gives you dictation that tidies up your words for free, with no word limit. Wispr Flow costs $15 a month, or $144 a year billed annually. Holding a key and talking in Infina is free with no word limit, with your words tidied up on your computer, and hands-free typing is $8.25 a month, billed annually at $99.