play_summaryLABSCO SUMMARY
The answer reaches you while your eyes are elsewhere.
It does one thing: turns text into speech and plays it without holding up the conversation. The persistence is what makes it comfortable in practice — you pick a voice and a tone once and every later summary arrives in it. Synthesis is billed to your own OpenAI key, so cost tracks how much you have read to you.
What it is
A text-to-speech output for whatever the assistant just wrote. It sends text to OpenAI's TTS models, plays the result through the platform's own audio player without blocking, and cleans up the temporary file afterwards. Voice and tone are saved between calls, so they are set once rather than passed every time.
What you get
- A summary spoken aloud and played in the background
- A voice chosen from ten OpenAI voices — alloy, ash, ballad, coral, echo, fable, nova, onyx, sage and shimmer — and remembered
- Delivery instructions saved as a tone, so how it is read is a preference rather than an argument
Requirements
Python 3.8 or higher and an OpenAI API key with access to the TTS models. macOS and Windows use their built-in players; on Linux one of mpg123, sox, ffmpeg, vlc or alsa-utils needs to be present.
Setup effort
Build from source — git clone https://github.com/FiveOhhWon/summarize-mcp.git
USE CASES
01
Hearing the outcome of a long build
The summary is spoken while you are looking at something else, and playback is backgrounded so the assistant carries on rather than waiting for the audio to end.
02
Getting through a document without reading it
Have the summary of an article or report read aloud on a commute or a walk, in a voice you picked rather than the platform default.
03
Setting how it should sound, once
Save the delivery you want — brisk, measured, conversational — as a tone, and every later summary is read that way without restating it.
04
Making one machine sound different from another
Different voices on different projects or machines makes it obvious which session just finished when several are speaking.
3 tools
Listed in project docs. Your client may show a different list.
set_voiceset_toneBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- Python 3.8 or later
- OPENAI_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/FiveOhhWon/summarize-mcp.git
cd summarize-mcp
pip install -e .MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"summarize": {
"command": "python",
"args": [
"<YOUR_PATH_TO_SUMMARIZE_MCP>/src/summarize_mcp/server.py"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}<YOUR_PATH_TO_SUMMARIZE_MCP> is the full path of your clone. Use the same python you ran pip install with.
