# Hands-Free Voice Prompting: The Complete Guide

> What hands-free voice prompting is, how it differs from push-to-talk dictation, who needs it, and how Infina's hands-free loop works on Mac.

Source: https://www.infina.so/hands-free-voice-prompting
Published: 2026-07-04. Last updated: 2026-09-14.
Category: Hands-free. Published by Infina (https://www.infina.so).

**About Infina.** Infina runs the whole prompt loop on three spoken words. Say "type" and your sentence and it types. Say "send it", or just "enter", and it presses Enter. Say "open Cursor" and it switches apps. No hotkey, no key held down, no touching the keyboard, from across the room. Not push-to-talk. There is no key to hold to start talking and no Enter to press to send, so prompting an AI tool costs zero keypresses. It runs on macOS (Apple Silicon) and Windows 10 and 11, transcribes on your own computer, and costs $8.25 a month, billed annually at $99, for unlimited words and commands. The Free plan gives 2,000 free words.

---

**TL;DR:** Hands-free voice prompting is working with AI tools ([Claude Code](https://docs.claude.com/en/docs/claude-code/overview), Codex, Cursor, ChatGPT) through the complete voice loop: say "type" plus your prompt, send it by voice, and switch to the next app, with zero key touches. Typing is the bottleneck in AI-heavy work, and Infina removes it: speak thousands of words of prompts a day, keep multiple agents busy, and ship faster. Infina is the Mac app built around this loop, on-device by default, for a flat $8.25 a month, billed annually at $99, with unlimited words and unlimited voice commands, and a 7-day refund.

**Hands-free is used loosely in this category, so here is the specific version of it.** 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.


We named the category, and the distinction underneath is real and easy to verify: every mainstream dictation tool still needs your hands twice per prompt.

## What hands-free voice prompting actually means

Watch someone use a normal dictation app with an AI tool and count the keyboard touches per prompt:

1. Hand moves to the keyboard to **hold the hotkey**.
2. They speak. Text appears.
3. Hand stays to **press Enter** and send it.
4. Hand goes to the trackpad or Cmd-Tab to **switch windows** for the next task.

The speaking part went hands-free; the loop around it didn't. Hands-free voice prompting closes all four:

- **Trigger by voice**: the trigger word "type" replaces the hotkey.
- **Dictate**: say "type" plus your words, in one breath, and Infina types them.
- **Send by voice**: a spoken command presses Enter for you.
- **Switch apps by voice**: "open Terminal" replaces Cmd-Tab.

The test is simple: can you run a full prompt, send, next-app cycle from three feet away, hands around a coffee mug? If any step needs a key, it's push-to-talk dictation wearing a costume.

## How it differs from push-to-talk dictation

Push-to-talk is what Wispr Flow, Superwhisper, and essentially every mainstream dictation app do: hold a hotkey, speak, release, and the tool's job ends the moment text lands. Some are very good at that slice, but they are hotkey-triggered and they stop at typing text.

| | Push-to-talk dictation | Hands-free voice prompting |
|---|---|---|
| **Trigger** | Hold a hotkey on the keyboard | Say "type" plus your words |
| **Sending** | You press Enter | Say "send it" and Enter is pressed for you |
| **App switching** | Cmd-Tab or trackpad | "Open [app]" by voice |
| **Hands on keyboard** | Every single dictation | Zero |
| **Works across the room** | No, you're at the keys | Yes, a few feet from the Mac |

To be clear about the neighbors: this isn't the same as classic *voice control* software either. Accessibility-grade voice control (like [Talon](https://talonvoice.com)) can drive a whole computer by voice, a deep and different discipline. If driving the whole Mac by voice is what you're after, we compare Apple's built-in Voice Control with Infina's voice commands in [how to control your Mac with your voice](/how-to-control-your-mac-with-your-voice).

Hands-free voice prompting is narrower and lighter: it optimizes one loop, the prompt cycle, for people who use AI tools all day. See the head-to-heads with [Wispr Flow](https://www.infina.so/wispr-flow-vs-infina) and [Superwhisper](https://www.infina.so/superwhisper-vs-infina) for how the push-to-talk tools compare in full.

## Who it's for

Three groups get a disproportionate payoff:

- **People running AI coding agents.** If you have Claude Code, Codex, or Cursor sessions open all day, your work is a stream of prompts across multiple windows. Hands-free turns "review here, instruct there" into one continuous motion, which is how one person keeps several agents shipping at once. The deep-dives are in [voice typing for Claude Code](https://www.infina.so/voice-typing-for-claude-code) and [voice typing for Cursor](https://www.infina.so/voice-typing-for-cursor). The broader workflow, describing changes to a coding agent by speaking, is [vibe coding by voice](/vibe-coding-by-voice).
- **People managing RSI or wrist pain.** Push-to-talk still demands hundreds of hotkey holds and Enter presses a day. Hands-free removes the residual keystrokes, not just the typing.
- **People who think while pacing.** Some brains produce better prompts standing at a whiteboard or walking a slow circle than hunched at a desk. If that's you, being tethered to a hotkey was the only thing stopping you.

If you dictate a few emails a week, push-to-talk (or free macOS dictation) is genuinely all you need. This category earns its keep at high prompt volume, where the time saved compounds daily.

## How Infina implements it

Infina is a Mac and Windows app whose base job is on-device dictation; hands-free is the layer on top. The mechanics:

1. **Double-tap Cmd (⌘)** to toggle hands-free mode on. It's off by default. Listening runs entirely on-device; nothing is recorded and nothing is sent anywhere while it waits.
2. Speak a sentence that starts with **"type"**: "type refactor the login flow but keep the animations". Infina types it straight into the focused app. No hotkey; "type" itself is the trigger. Transcription runs on your Mac by default (on the Apple Neural Engine), so the whole loop works offline. See [on-device dictation for Mac](https://www.infina.so/on-device-dictation-mac).
3. Say **"send it"**: Infina presses Enter.
4. Say **"open Terminal"** (or "open Cursor", "open Notes", any app) and repeat.

It's designed to work from two to three feet away, normal leaning-back-in-your-chair distance. Prefer a keyboard escape hatch? Double-tapping Ctrl wakes it for a single command while hands-free is on, and hold-Option push-to-talk always works regardless.

Pricing is deliberately flat and unmetered: $8.25 a month, billed annually at $99 (at the time of writing) for unlimited words and unlimited voice commands, a 7-day no-questions refund, and an optional $5/month cloud add-on (billed annually at $60) for polished output and more languages. Details on [pricing](https://www.infina.so/pricing).

For anyone speaking thousands of words of prompts a day, that is the whole cost: no per-word charge, no per-minute meter, no per-seat maths.

## Honest limits

The fine print, up front:

- **It's labeled experimental.** Hands-free is our newest surface. It ships off by default, and push-to-talk is the mature fallback when the trigger word mishears.
- **English only in the base product.** The cloud add-on brings more languages, but hands-free is not yet a polyglot experience.
- **Mac and Windows, no phone app.** On a Mac the on-device models need Apple Silicon. Windows gets voice typing, hands-free, and the commands that drive the computer; reading your screen and rewriting selected text stay Mac-only. See [Infina for Windows](/docs/windows).
- **A quiet-ish room helps.** Picking up your voice at a distance is physics: a blasting fan or open-plan chatter degrades it. It doesn't need silence, but it's happiest in a normal home office.
- **Free plan.** You get 2,000 free words, no card required, so you can find out whether hands-free sticks in your room with your accent before paying. After that, a 7-day money-back guarantee means the refund is one email.

None of these change the core claim: for the prompt loop itself, nothing else on the Mac runs it end to end by voice.

## FAQ

**What is hands-free voice prompting in one sentence?**
Prompting AI tools through a fully voice-driven loop (say "type" plus your prompt, send, and switch apps) with zero keyboard touches.

**How is it different from dictation apps like Wispr Flow or Superwhisper?**
Those are push-to-talk: a hotkey triggers them, and their job ends when text appears, so sending and window-switching stay on your hands. Hands-free voice prompting covers the whole cycle by voice.

**Is my Mac recording everything while hands-free mode is listening?**
No. Infina's hands-free listening runs on-device inside the app; nothing is recorded or sent anywhere while it waits for you to speak. By default, transcription is also on-device and no audio or transcripts are stored.

**Does it work with Claude Code, Cursor, and Codex?**
Yes. Infina types into whatever app is focused, at the OS level, so it works with any terminal, editor, or chat window. No per-app extension needed.

**What do I need to run it?**
A Mac with Apple Silicon (M-series). The base product is English-only; the optional $5/month cloud add-on adds more languages and polished output.

**How much does Infina cost?**
$8.25 a month, billed annually at $99 (at the time of writing), including every update, with a 7-day no-questions-asked money-back guarantee. Unlimited words and voice commands, and a Free plan of 2,000 free words, no card required for the core product.

## The bottom line

Dictation apps solved speaking-instead-of-typing years ago. What they never solved is the loop around it (trigger, send, switch), which still runs through your hands.

If you prompt AI tools occasionally, that residue doesn't matter and free dictation is fine. If prompting *is* your workday, hands-free voice prompting is a different way of working: you review with your eyes, direct with your voice, keep multiple agents busy, and do more in less time.

Infina is the tool built for exactly that loop, at $8.25 a month, billed annually at $99. If it doesn't earn its place in a week, the refund takes one email.

---

## Hands-free, and what the alternatives do instead

Only two tools on this list are hands-free in the full sense. Here is what each of the others asks of your hands, and who should still pick it.

The tools this page covers (Wispr Flow, Superwhisper, Talon) 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. |
| 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. |
| 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. |
| 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. |
| 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. |

### 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.