Skip to content
Back to skills

Voicemode Setup

ASecurity

Setup guide for VoiceMode — natural voice conversations with Claude Code via Whisper + Kokoro

  • 6 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added May 27, 2026
developmentpythongobashgitapi

Works with

  • claude code
  • api
  • mcp

Security analysis

A96/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned May 27, 2026

npx -y skills add KevinZai/commander --skill voicemode-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Voicemode Setup?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Voicemode Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kevinzai-voicemode-setup/badge)](https://www.skillsdirectory.com/skills/kevinzai-voicemode-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: voicemode-setup
description: Setup guide for VoiceMode — natural voice conversations with Claude Code via Whisper + Kokoro
category: integrations
triggers:
  - voice
  - speech
  - voicemode
  - whisper
---

# VoiceMode Setup

Natural 2-way voice conversations with Claude Code via the VoiceMode MCP server (mbailey/voicemode).

## When to Use
- Hands-free coding sessions
- Dictating requirements or reviewing code verbally
- Accessibility — voice as an alternative to typing

## Quick Start
```bash
# Install via pip
pip install voicemode

# Or clone and install
git clone https://github.com/mbailey/voicemode.git
cd voicemode && pip install -e .
```

## Claude Code MCP Configuration

Add to your project's `.claude/settings.json`:
```json
{
  "mcpServers": {
    "voicemode": {
      "command": "voicemode",
      "args": ["serve"]
    }
  }
}
```

## Audio Stack
- **STT (Speech-to-Text):** OpenAI Whisper (local or API)
- **TTS (Text-to-Speech):** Kokoro (local, fast) or OpenAI TTS (cloud, higher quality)
- **Streaming:** LiveKit for real-time audio

## Prerequisites
- Python 3.10+
- Audio input device (microphone)
- For local STT: sufficient RAM for Whisper model
- For cloud STT/TTS: OpenAI API key

## Reference
- Repository: github.com/mbailey/voicemode
- License: MIT
- Stars: 937+

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.