---
title: 'Voice Dictation for Claude Code on macOS'
excerpt: 'Drive Claude Code by voice: hold a hotkey, speak the prompt, and Keebye types it into your terminal — on-device, offline, terminal-aware.'
date: '2026-07-14'
author: 'Teodor Deleanu'
tags: ['claude-code', 'dictation', 'terminal']
keywords: ['dictation for claude code', 'voice input claude code', 'speak prompts claude code']
faq:
  - question: 'Does Keebye work inside a terminal running Claude Code?'
    answer: 'Yes. Keebye inserts text into whatever app has focus, and it detects terminals and switches to chunked synthetic typing so long prompts arrive intact instead of overflowing the input.'
  - question: 'Does Claude Code or Anthropic ever see my audio?'
    answer: 'No. Transcription happens on your Mac and the audio never goes anywhere. What reaches Claude Code is the finished text, the same as if you had typed it.'
  - question: 'Does it work offline?'
    answer: 'Yes. Once the one-time model download finishes, transcription runs fully local with no connection needed — though Claude Code itself of course needs one to reach its model.'
  - question: 'How do I start and stop dictating?'
    answer: 'Hold Right Command while you speak and release to drop the text into the session — or tap once to toggle for longer prompts. Esc abandons a dictation mid-flight. Fn and Right Option are the built-in alternative hotkeys if Right Command clashes with something.'
  - question: 'Can it learn project-specific terms?'
    answer: 'Yes. Add names like your repo, branch, or framework terms to the custom dictionary so they transcribe correctly.'
---

## Why dictate prompts to Claude Code

Working with a coding agent changes what you type. The unit of work is no longer the code line — it's the prompt paragraph. You describe the change you want, the constraints, the files involved, and the agent does the rest. Multi-sentence instructions like that are faster and less tiring to speak than to type, and the gap widens when you're doing it dozens of times a day.

This is exactly the scenario Keebye was built for: [builders running several agent workstreams at once](/dictation-for/vibe-coders), narrating instructions to each one instead of typing them. When three terminals each have a Claude Code session waiting for direction, speaking the next prompt keeps you moving between them.

## How it works

Focus the terminal running Claude Code, hold Right ⌘, and talk. Release, and the transcript lands right in the Claude Code input, ready to send or edit.

A terminal is a [special case for getting text in](/dictation-for/terminal), and Keebye treats it as one. When the app in focus is a terminal, it shifts into chunked synthetic typing rather than one big paste, so a long multi-sentence prompt arrives whole instead of garbled.

Everything runs on your Mac: Parakeet, the default English model, transcribes on-device, and once its one-time download is done, no network is needed and nothing is phoned home. Your audio stays local — Claude Code just sees text, the same as if you'd typed it.

## Setup in two minutes

Setup is short: install the app, approve the Accessibility and microphone prompts, and choose a hotkey. Right ⌘ is the default; Fn and Right ⌥ ship as alternatives. With launch-at-login on, Keebye is up before your first session is.

Then give the custom dictionary a minute: repo names, tool names, the project jargon you repeat all day. That's what makes them come out right on the first pass.

## Limits, honestly

One expectation to set: Keebye transcribes when you release the key, not while you talk. There are no live streaming captions — you speak, let go, and the full prompt appears at once.

Keebye is macOS only.