voice-mcp CLAUDE.md

voice-mcp CLAUDE.md is an instructions file for Claude Code from shreyaskarnik/voice-mcp. It costs 614 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for voice-mcp, a local voice server that converts speech to text and text to speech.

In plain words
What is it for?
Use them when developing or operating this Apple Silicon voice server, including its recording, speech recognition, and speech synthesis features.
Why use it?
They explain how the project works, how to run it, and constraints such as keeping logs off the standard output used for communication.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions 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 instructions/shreyaskarnik/voice-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/shreyaskarnik/voice-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for voice-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shreyaskarnik/voice-mcp/claude-md.svg)](https://agentmods.dev/instructions/shreyaskarnik/voice-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shreyaskarnik/voice-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shreyaskarnik/voice-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 614 This file is loaded in full into every session.
When invoked 614 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.00614 $0.00614
Opus 5 $0.00307 $0.00307
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00061 $0.00061

Measured 6d ago against content hash 60bc2876c3dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

voice-mcp CLAUDE.md scanned grade A with 0 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

voice-mcp is a bidirectional voice MCP server for Claude Code (and other MCP-compatible agents). It exposes two tools — listen() (STT) and speak() (TTS) — that run locally on Apple Silicon via mlx-audio. The entire server is a single file: server.py.

Commands

uv sync              # Install dependencies
uv run server.py     # Start the MCP server (stdio transport)

There is no test suite, linter, or build step.

Architecture

Single-file server (server.py, ~273 lines) built on FastMCP (from the mcp SDK). Communicates over stdio — stdout is the MCP JSON-RPC channel, so all logging goes to stderr.

Key components:

  • Lifespan hook — pre-loads STT and TTS models at startup so first tool call is fast
  • Lazy singletonsget_stt_model() / get_tts_model() load models once from HuggingFace MLX Community repos
  • VAD recordingrecord_until_silence() uses webrtcvad (mode 3) with energy-based fallback; stops after 1.5s of silence
  • Audio cueschime_listening() / chime_done() synthesize short tones via numpy+sounddevice to signal mic state
  • TTS playbackspeak() redirects stdout to /dev/null during playback because mlx-audio's AudioPlayer prints to stdout, which would corrupt the MCP stdio channel

Models:

  • STT: mlx-community/Voxtral-Mini-4B-Realtime-2602-int4 (16 kHz input)
  • TTS: mlx-community/Kokoro-82M-bf16 (24 kHz output, 54 voices across 9 languages)

Hooks (.claude/settings.json + .claude/hooks/notify.sh):

  • PreToolUse on mcp__voice__listen — shows macOS notification and forces permission prompt for mic access
  • PreToolUse on mcp__voice__speak — shows notification with text preview
  • PostToolUse on mcp__voice__listen — shows notification with transcription result

Important Constraints

  • stdout is sacred: Never print to stdout in server code. All logging must use log.*() (configured to stderr). The speak() function's stdout redirect pattern exists for this reason.
  • macOS + Apple Silicon only: mlx-audio requires Metal (Apple GPU). No CPU/CUDA fallback.
  • mlx-audio installed from git main: The mlx-audio dependency is pinned to the GitHub main branch, not PyPI.

Read the full file on GitHub · 43 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. 6d ago First seen · 43 lines · 614 tokens per session scan A 60bc2876c3dc

Subscribe to this mod's changes

voice-mcp CLAUDE.md is an instructions file published in the GitHub repository shreyaskarnik/voice-mcp (16 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 614 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens