# Hands-Free Claude Code: Run Agent Sessions From Across the Room

> How to run hands-free Claude Code sessions: dictate, send, and switch terminals entirely by voice, plus setup steps and honest limits.

Source: https://www.infina.so/hands-free-claude-code
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 Claude Code means running your agent sessions entirely by voice: speak a sentence that starts with "type", say "send it" (or just "enter"), then switch terminals by voice and queue the next instruction, all from 2 to 3 feet away. Dictation apps still make you touch the keyboard to trigger and send; Infina completes the whole prompt, send, switch-app loop hands-free, with on-device transcription. It is $8.25 a month, billed annually at $99 (at the time of writing) with a 7-day refund, flat, with unlimited words and unlimited voice commands no matter how many sessions you run.

If you are new to dictating prompts at all, start with [voice typing for Claude Code](https://www.infina.so/voice-typing-for-claude-code), our guide to speaking prompts into a session with push-to-talk. This article is the next level: running Claude Code without the keyboard at all.

## What hands-free Claude Code looks like

[Claude Code](https://code.claude.com/docs) is an agent. You give it an instruction, it works for a while, you review and redirect. Between instructions there is nothing for your hands to do.

So why are you sitting at the keyboard?

With Infina's hands-free mode on, a Claude Code session runs like this:

1. Speak a sentence that starts with **"type"**, like "type refactor the login flow but keep the animations". Infina types it straight into the focused terminal.
2. Say **"send it"**. Infina presses Enter.
3. Claude Code gets to work. You stand up, stretch, read the previous diff on screen.
4. Say **"open Terminal"**, then say **"type"** plus the next session's instruction.

No hotkey to hold, no Enter to press, no Cmd-Tab. It all works from 2 to 3 feet away, which is normal leaning-back or standing-at-the-desk distance, and that distance is the core feature.

This is the difference between dictating into Claude Code and using Claude Code by voice. The first saves your fingers some typing. The second changes where you can be and how many sessions you can run.

## Setup: from install to first voice-sent prompt

Setup takes about two minutes:

1. **Install Infina** and grant the microphone and accessibility permissions it asks for. It types at the OS level, so it works in Terminal.app, iTerm, Warp, and the VS Code terminal alike.
2. **Double-tap Cmd (⌘)** to toggle hands-free mode on. It is off by default.
3. Open your Claude Code session and speak a sentence that starts with **"type"**. Say **"send."**

That is the whole loop. Hands-free listening runs on-device (nothing is recorded or sent anywhere while it waits for you to speak), and transcription runs on your Mac's Neural Engine by default, so it all works offline and your audio never leaves your device.

Two escape hatches worth knowing. **Double-tap Ctrl** wakes Infina for a single command while hands-free is on. And **holding Option** is classic push-to-talk dictation, which always works regardless of mode.

## The voice commands that matter for Claude Code

Claude Code voice control is not a hundred memorized commands. The working set is small:

| You say | What happens |
|---|---|
| **"type" + your prompt** | Types your words straight into the focused app |
| **"send it"** | Presses Enter |
| **"new line"** | Inserts a line break, for multi-paragraph prompts |
| **"open [app]"** | Opens or focuses an app by name |
| Tab commands | Moves between tabs, for multi-tab terminal setups |

That covers the entire Claude Code loop: compose, send, navigate, repeat. The broader philosophy of the loop is in [hands-free voice prompting](https://www.infina.so/hands-free-voice-prompting).

One tip for long prompts: say "new line" between the goal, the context, and the constraints. Claude handles a wall of words fine, but the structure keeps *you* honest while speaking.

## Multiple Claude Code sessions, all busy, zero keystrokes

Here is where hands-free stops being a convenience and becomes a multiplier.

A single Claude Code session leaves you idle while the agent works. The fix is well known: run two or three sessions on different tasks. The problem is that feeding several sessions by keyboard means constant Cmd-Tab, click, type, Enter, and most people fall back to one.

By voice, rotating through sessions is one continuous motion:

- Session one finishes a refactor. You read the diff and say: "Type. Looks right, now update the tests to match and run them. Send."
- "Open Terminal." Session two is waiting on input: "Type. Yes, go with option two, but keep the old config keys working. Send."
- Session three has been quietly writing docs. You glance, approve, queue its next file.

You review while agents work and you queue the next instruction without sitting down. The keyboard stops being the thing that caps how many agents one person can direct.

We wrote a whole economics piece on this pattern: [run multiple AI agents by voice](https://www.infina.so/voice-prompting-multiple-agents). The same loop drives Cursor and Codex windows too, since Infina types into whatever app is focused.

## Honest limits

Before you buy, the fine print:

- **Hands-free is our newest feature and labeled experimental in the app.** It ships off by default. Hands-free listening at a distance likes a quiet-ish room; a loud fan or open-plan chatter degrades it. Push-to-talk is the mature fallback that always works.
- **English only in the base product.** The optional $5/month cloud add-on (billed annually at $60) adds more languages and polished output from large language models, useful if you also dictate emails and docs in the same app.
- **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).
- **Raw output by design.** Perfect for prompts, since Claude does not care about your commas; not meant for publishing prose without the add-on.

And to be precise about the claim: plenty of apps dictate. What they leave on your hands is triggering, sending, and switching windows. Infina is built so the whole loop, not just the middle of it, runs by voice.

## FAQ

**Can I use Claude Code without touching the keyboard?**
Yes, with Infina's hands-free mode: speak a sentence that starts with "type", say "send it", and switch between terminals and apps by voice. Typing, sending, and window-switching are all handled for you.

**How far away does hands-free Claude Code work?**
Infina's hands-free mode works from 2 to 3 feet away, which covers leaning back in your chair or standing at your desk. It is designed for that distance as a core feature, not a party trick.

**Does Claude Code understand rough, unpunctuated dictation?**
Yes. Claude parses conversational, unpolished speech, filler words included, so raw dictation loses nothing versus typed prompts. That is why Infina's base product optimizes for raw speed instead of prose polish.

**Is Infina listening to everything while hands-free is on?**
No. Hands-free listening runs on-device inside the app, and nothing is recorded or sent anywhere while it waits for you to speak. Transcription is also on-device by default, and privacy mode is on by default so no audio or transcripts are stored.

**Can I manage multiple Claude Code sessions this way?**
Yes, that is the killer use case. Dictate to one session, say "send it", say "open" plus the next terminal's name, and repeat, keeping two or three agents busy in parallel without sitting down.

**What does Infina cost?**
$8.25 a month, billed annually at $99 (at the time of writing), every update included, with a 7-day no-questions-asked money-back guarantee. It is flat, with unlimited words and unlimited voice commands, plus a Free plan of 2,000 free words, no card required; the optional cloud add-on is $5/month billed annually with its own 7-day trial. Details on [pricing](https://www.infina.so/pricing).

## The bottom line

Claude Code already removed the typing from coding. Hands-free Claude Code removes the keyboard from the loop that remains: instruct, review, redirect, all by voice, from wherever you happen to be standing.

If you run one session for twenty minutes a day, push-to-talk is plenty, and [voice typing for Claude Code](https://www.infina.so/voice-typing-for-claude-code) covers that. If Claude Code is open from morning to evening, the hands-free loop is the version that compounds: more instructions, more sessions, more shipped.

Infina runs that loop for $8.25 a month, billed annually at $99, on-device by default, risk-free for 7 days.

---

## 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.

None of these is the wrong answer for everybody. What differs is which reader each one is right for.

| 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. |
| 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. |
| 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. |

### 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.