F
licenseNot graded
qualityD
maintenanceEnables AI agents to generate and play high-quality text-to-speech audio using the Kokoro model, with support for multiple voices, adjustable speaking speed, and audio caching.
-
glados-voice-mcp
by bkmeneguello
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@glados-voice-mcptell me that the system requires a reboot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
glados-voice-mcp
A warm, shared GLaDOS text-to-speech server for agents, exposed as an MCP tool. It builds on nimaid/GLaDOS-TTS, included unmodified as a git submodule.
Using an AI agent? Point it at this repository and ask it to follow
AGENTS.md; it contains every step to install, register and verify the server.
Fast: about 100 ms to first audio once the models are loaded; text is split into sentences and the first one plays while the rest is still being synthesized.
Lazy and shared: the MCP process is a thin proxy. The first
speakstarts one shared daemon (127.0.0.1:18765) that loads the models, serves every agent on one audio device, and exits after 10 minutes without requests or speech.In character: the persona is part of the tool description and
speakrejects calls within_character=false. The server cannot verify the style of the text itself.One voice at a time: if a message is loading or playing,
speakreturnsBUSY ... Retry in about N secondsso agents never talk over each other.stopcuts speech for everyone.
Install
No clone or project directory is needed: uv installs straight from this repository (including the submodule). Pick exactly one onnxruntime extra: cpu or cuda (NVIDIA, CUDA 13 wheels). Replace https://github.com/bkmeneguello/glados-voice-mcp with this repository's URL.
# 1. Build the environment and download the models once (about 125 MB, stored in your user data dir)
uvx --from "glados-voice-mcp[cpu] @ git+https://github.com/bkmeneguello/glados-voice-mcp" glados-voice download-models
# 2. Try it (plays audio)
uvx --from "glados-voice-mcp[cpu] @ git+https://github.com/bkmeneguello/glados-voice-mcp" glados-voice say "Hello, test subject."Prefer a persistent command? uv tool install "glados-voice-mcp[cpu] @ git+https://github.com/bkmeneguello/glados-voice-mcp" or pipx install "..." puts glados-voice-mcp on your PATH. To develop, clone with git clone --recurse-submodules https://github.com/bkmeneguello/glados-voice-mcp and run uv pip install ".[cpu]" in a venv.
Related MCP server: mcp-ai-voice
Register the MCP server
claude mcp add glados-voice -- uvx --from "glados-voice-mcp[cpu] @ git+https://github.com/bkmeneguello/glados-voice-mcp" glados-voice-mcpFor other clients use the command uvx with the arguments --from "glados-voice-mcp[cpu] @ git+https://github.com/bkmeneguello/glados-voice-mcp" glados-voice-mcp; AGENTS.md has Codex, Gemini and JSON examples.
Tools: speak(text, in_character, wait=false), stop(), status().
Configuration (environment variables)
Variable | Default | Meaning |
|
| Idle time before the daemon exits and unloads the models |
|
| Localhost port of the shared daemon |
|
|
|
| OS user data dir | Model files, e.g. |
The daemon log is glados_voice_daemon.log in the system temp directory. The daemon accepts requests from any local process and has no authentication.
Python use
from glados_voice import VoiceEngine
engine = VoiceEngine().start() # loads in the background
engine.speak("Hello. This is a test.")
engine.wait_idle()Credits and license
MIT, see LICENSE and NOTICE.md. Voice models come from dnhkng/GlaDOS and are downloaded at first use, not stored here.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
AI voice generation: text-to-speech and voice cloning from any MCP client.
Let cloud agents talk to you: progress updates spoken on your Mac, and replies you send back.
Command your AI agents by voice: PTT rooms, channels, direct messages, agent email, memory (mRAG).
Giggy speech tools for AI agents: discover voices and generate text-to-speech.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to synthesize natural speech using either platform system voices or premium OpenAI TTS, with automatic engine selection and graceful fallback.112 npmMIT
- AlicenseAqualityAmaintenanceEnables AI agents to speak using MacOS native text-to-speech, with support for blocking and non-blocking speech and a sequential queue.215MIT
- AlicenseNot gradedqualityCmaintenanceEnables 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