install

An installation command for VoiceMode and its local voice-processing services. FFmpeg processes audio, Whisper converts speech to text, and Kokoro converts text to speech.

In plain words
What is it for?
It is for installing and checking VoiceMode, FFmpeg, Whisper, and Kokoro services on Apple Silicon Macs, then reconnecting the voice service.
Why use it?
It removes the manual work of installing the command-line tools and dependencies needed for local voice conversations.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mbailey/voicemode/install
Clone the repo
git clone --depth 1 https://github.com/mbailey/voicemode

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 615 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00615
Opus 5 $0.00005 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00061

Measured 2d ago against content hash 2bda97099530, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

install scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **UV** - Python package manager (install: `curl -LsSf https://astral.sh/uv/install.sh | sh`)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **UV** - Python package manager (install: `curl -LsSf https://astral.sh/uv/install.sh | sh`)
.claude/commands/install.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voicemode:install

Install VoiceMode and all dependencies needed for voice conversations.

Quick Install (Non-Interactive)

For a fast, fully automated install on Apple Silicon:

uvx voice-mode-install --yes
voicemode service install whisper
voicemode service install kokoro

What Gets Installed

Component Size Purpose
FFmpeg ~50MB Audio processing (via Homebrew)
VoiceMode CLI ~10MB Command-line tools
Whisper (base) ~150MB Speech-to-text
Kokoro ~350MB Text-to-speech

Implementation

  1. Check architecture: uname -m (arm64 = Apple Silicon, recommended for local services)

  2. Check what's already installed:

    which voicemode  # VoiceMode CLI
    which ffmpeg     # Audio processing
    
  3. Install missing components:

    # Full install (installs ffmpeg, voicemode, and checks dependencies)
    uvx voice-mode-install --yes
    
    # Install local services
    voicemode service install whisper
    voicemode service install kokoro
    
  4. Verify services are running:

    voicemode service status whisper
    voicemode service status kokoro
    
  5. Reconnect MCP server: After installation, the VoiceMode MCP server needs to reconnect:

    • Run /mcp and select voicemode, then click "Reconnect", OR
    • Restart Claude Code

Whisper Model Selection

For Apple Silicon Macs with 16GB+ RAM, the large-v2 model is recommended:

Model Download RAM Usage Accuracy
base ~150MB ~300MB Good (default)
small ~460MB ~1GB Better
large-v2 ~3GB ~5GB Best (recommended for 16GB+ RAM)
large-v3-turbo ~1.5GB ~3GB Fast & accurate

To install the recommended model:

voicemode whisper install --model large-v2

Prerequisites

This install process assumes:

  • UV - Python package manager (install: curl -LsSf https://astral.sh/uv/install.sh | sh)
  • Homebrew - macOS package manager (install: brew.sh)

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 85 lines · 11 tokens per session scan C 2bda97099530

Subscribe to this mod's changes

install is a command published in the GitHub repository mbailey/voicemode (1,346 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 615 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.