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.
npx agentmods add commands/enesbasbug/voice-to-claude/setupgit clone --depth 1 https://github.com/enesbasbug/voice-to-claudeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00544 |
| Opus 5 | $0.00009 | $0.00272 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade C, and why
setup scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf build How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
voice-to-claude Setup
Run the setup script directly. Do not manually check prerequisites - the script handles everything automatically.
Instructions
IMPORTANT: Run the command below directly. Do NOT manually check Python version or install dependencies first - the setup script handles all of this automatically.
python3.10 ${CLAUDE_PLUGIN_ROOT}/scripts/setup.py 2>/dev/null || python3.11 ${CLAUDE_PLUGIN_ROOT}/scripts/setup.py 2>/dev/null || python3.12 ${CLAUDE_PLUGIN_ROOT}/scripts/setup.py 2>/dev/null || python3 ${CLAUDE_PLUGIN_ROOT}/scripts/setup.py
The script will:
- Auto-detect Python 3.10+ (works with 3.10, 3.11, or 3.12)
- Create a local
.venvin the plugin directory - Install dependencies in the venv (isolated)
- Build whisper.cpp with Metal support (~3-5 min)
- Download the Whisper model (~142MB)
- Configure everything
Important: Do not manually check Python version or install dependencies - the script does this automatically.
Step 2: Handle Common Errors
"Microphone permission denied" (macOS):
macOS requires Microphone permission for audio recording.
1. Open System Settings > Privacy & Security > Microphone
2. Find your terminal app (Terminal, iTerm, etc.) and enable it
3. Re-run: /voice-to-claude:setup
"Accessibility permission needed" (macOS):
macOS requires Accessibility permission for keyboard input.
1. Open System Settings > Privacy & Security > Accessibility
2. Find your terminal app and enable it
3. Re-run: /voice-to-claude:start
cmake or build errors:
# Ensure Xcode tools are installed
xcode-select --install
# Try rebuilding
cd ~/.local/share/voice-to-claude/whisper.cpp
rm -rf build
cmake -B build -DGGML_METAL=ON
cmake --build build -j
PortAudio errors:
brew install portaudio
Success
When setup completes successfully, you'll see:
Setup Complete!
To start voice dictation:
/voice-to-claude:start
Then hold Ctrl+Alt and speak!
Use /voice-to-claude:start to start the daemon.
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.
- 3d ago First seen · 76 lines · 17 tokens per session scan C cec2a10c137c
setup is a command published in the GitHub repository enesbasbug/voice-to-claude (10 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 544 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
add
Add a word to your voice vocabulary.
fix
Teach idiolect what the recogniser misheard.
status
Check the idiolect relay, settings and vocabulary.
recent
Show recent voice transcripts and corrections.
remove
Remove a word from your voice vocabulary.
wheel-to-talk-stop
Stop the Wheel to Talk backend.