Skip to main content
Glama

speak-mcp

An MCP server that lets a coding agent speak out loud, offline, on the CPU. It's part of Voice Coding: coding agents for people who can't see the screen.

  • One tool: speak(text, lang, wait).

  • Text-to-speech runs in-process with Kyutai Pocket TTS: no API key, no HTTP server.

  • lang is fr, en, de, es, it, pt or nl. Each language model loads on first use, so the agent picks the language on every call.

  • Calls play in order, so two sentences never overlap, even across sessions: a machine-wide named mutex lets one speak-mcp process play at a time. wait: false (the default) returns at once and the agent keeps working.

  • Only the main agent speaks. The server instructions tell subagents and delegated tasks to report to their parent instead.

  • Windows only for now: playback uses winsound.

Install

Install the plugin in Claude Code:

/plugin marketplace add Guillaume-de-Maleprade/speak
/plugin install speak@speak

It's also listed in the g2m marketplace as speak@g2m.

Then run /speak:setup. It installs mcp and pocket-tts into the python on PATH (the one the server starts with), downloads the voice model, and plays a test sentence. Expect 1-3 minutes: it downloads torch. To do it by hand instead:

python -m pip install "mcp>=2.3,<3" "pocket-tts>=4.0,<5"

To test the local copy without installing it, from the repo root:

claude --plugin-dir .

Options, as environment variables:

Variable

Default

Meaning

SPEAK_LANG

fr

Language when a call gives none

SPEAK_PRELOAD

SPEAK_LANG

Comma-separated languages to load at startup; empty to load nothing

SPEAK_PREFIX

git repo name

Said before every message, so you know which session talks; empty to say nothing

SPEAK_DELAY_S

2

Seconds between a call and the start of its playback, so the reply written after the call is on screen when the voice starts; 0 to play at once

Related MCP server: ThotStream

Turn it off

The voice can get in the way: in a meeting, on a call, or when you just want quiet. Disable the plugin from a terminal:

claude plugin disable speak@speak

Turn it back on:

claude plugin enable speak@speak

Installed from the g2m marketplace? Use speak@g2m instead. You can also toggle it inside Claude Code with /plugin. Either way, the MCP server starts and stops with the plugin; restart the session for the change to apply.

Measured on a Windows laptop CPU (2026-11-12)

Step

Time

MCP handshake

0.7 s (torch is imported later, in the worker)

Import + load the first language

~3.6 s, once per session

Load another language

~1 s

Generate a 2–3 s sentence

0.3–0.7 s (4–5x real-time)

Licenses

Code: MIT. Pocket TTS: MIT code, CC-BY 4.0 weights; each voice has its own license (see kyutai/tts-voices on Hugging Face).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to narrate internal thoughts, announce tool actions, and speak final responses aloud through local cross-platform text-to-speech. It exposes dedicated audio tools over stdio JSON-RPC for MCP-compatible clients.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables an AI assistant to have its recent code actions summarized aloud through system speakers, using offline native voices or cloud neural voices. It supports asynchronous playback and voice listing so users can hear what the agent did without reading the full response.
      3
      35 PyPI
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to give spoken output by synthesizing text into speech with an on-device neural model and playing it through the user's speakers, entirely offline. Agents can queue spoken summaries and stop playback on demand.
      4 npm
      MIT