whatisgithub

What is voice-claude?

pietro-guiotto/voice-claude — explained in plain English

Analysis updated 2026-05-18

1PythonAudience · developerComplexity · 2/5Setup · moderate

In one sentence

Voice-claude lets you talk to Claude Code by holding a key, speaking, and having your words transcribed on-device and submitted as text.

Mindmap

mindmap
  root((voice-claude))
    What it does
      Push-to-talk voice input
      On-device transcription
      Submits text to Claude
      Flags speech-origin input
    Tech stack
      Python
      Apple Speech Recognition
    Use cases
      Hands-free coding commands
      Menu navigation by voice
    Audience
      Claude Code users
      macOS developers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Give Claude Code instructions by voice instead of typing, using a push-to-talk key.

USE CASE 2

Navigate Claude Code's menu prompts by speaking numbers aloud.

USE CASE 3

Use on-device speech transcription to avoid sending audio to external services.

USE CASE 4

Learn how to wrap a terminal AI tool with a local speech input layer.

What is it built with?

PythonmacOS Speech Recognition

How does it compare?

pietro-guiotto/voice-claudea-bissell/unleash-liteabhiinnovates/whatsapp-hr-assistant
Stars111
LanguagePythonPythonPython
Setup difficultymoderatehardhard
Complexity2/54/53/5
Audiencedeveloperresearcherdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

macOS only, requires granting microphone, accessibility, and speech recognition permissions.

License is not stated in the available README content.

So what is it?

Voice-claude is a Python wrapper for Claude Code, a terminal-based AI coding assistant, that lets you give instructions by speaking instead of typing. Hold a key, say what you want, release the key, and your words are automatically transcribed and submitted to Claude as if you had typed them yourself. The tool listens for the Right Option key on your keyboard. While held, it records your voice. On release, it uses Apple's Speech Recognition framework to convert the audio to text and types it into Claude. Transcription happens on your device, and no audio is sent to any external service. The tool also tells Claude that input came from speech recognition, so Claude knows to ask for clarification when a transcription sounds unclear rather than acting on a garbled command. Spoken numbers like one, two, three are converted into digits, useful for selecting options in Claude's menu prompts. The README describes this as a prototype and strongly warns against running Claude with full permissions. Transcription errors can cause Claude to receive incorrect instructions, potentially leading to deleted files, force-pushed branches, or unintended commits. Using the most restrictive permission mode available is recommended so destructive actions still require manual approval. The tool runs on macOS only and relies on Apple's Speech Recognition framework and system sounds. It requires Homebrew, Python 3.10 or newer, and Claude Code already installed. Your terminal application needs microphone, accessibility, and speech recognition permissions granted in macOS system settings before it will work. Because it types directly into whatever application has focus, voice-claude is not limited to Claude Code in principle, but the README frames it specifically as a companion for that tool and tests it in that context.

Copy-paste prompts

Prompt 1
Walk me through installing voice-claude with Homebrew and Python 3.10 on macOS.
Prompt 2
Which macOS permissions do I need to grant my terminal app for this tool to work?
Prompt 3
Explain why this project recommends running Claude Code in a restrictive permission mode.
Prompt 4
How does voice-claude tell Claude that a command came from speech recognition?

Frequently asked questions

What is voice-claude?

Voice-claude lets you talk to Claude Code by holding a key, speaking, and having your words transcribed on-device and submitted as text.

What language is voice-claude written in?

Mainly Python. The stack also includes Python, macOS Speech Recognition.

What license does voice-claude use?

License is not stated in the available README content.

How hard is voice-claude to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is voice-claude for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.