speakLABSCO SUMMARY
Output you can listen to instead of read.
The in-text markers are what lift it above a novelty: pauses, emphasis and rate changes are placed in the text itself, so a long passage comes out paced rather than flat, and background mode means the agent keeps working while it plays.
What it is
A text-to-speech server built on macOS's own say command, so the voices are the ones already installed on the system, including the premium ones you add through System Voice settings. It runs the speech in the foreground or in the background so the session can carry on talking while it plays.
What you get
speak— says the text aloud.voicechooses which one, defaulting to Alex;ratesets words per minute, defaulting to 175 within a range of 1 to 500;backgroundlets the session continue while speech plays- In-text control:
[[slnc 500]]inserts silence,[[rate 200]]changes speed mid-sentence,[[volm 0.5]]changes volume,[[emph +]]and[[emph -]]add and remove emphasis, and[[pbas +10]]shifts pitch list_voices— every text-to-speech voice available on the machine, which is how you find out what the premium and localised ones are called- A table of recommended voices with their language, region and the exact CLI specification to pass
Requirements
macOS, since it drives the system's own say command, and Node.js >= 14.0.0. Install with npm install say-mcp-server and point your client at the built index.js. Voices beyond the defaults are added through macOS System Voice settings, not through this server — so if list_voices does not show the one you want, install it there first.
Setup effort
One command — npm install say-mcp-server
USE CASES
01
Listening to something while you do other work
Send the passage in background mode so the speech plays while the assistant carries on with the next step.
02
Hearing an alert rather than watching for it
Have a long-running task announce itself out loud when it finishes.
03
Getting the pacing right on a long passage
Place silence, rate and emphasis markers in the text so it is read the way you would read it, not at one flat speed.
04
Picking a voice worth listening to
List what is installed on the machine and try the ones the README recommends, with the exact voice names to pass.
05
Reading foreign-language text properly
Choose a voice for that language and region so the pronunciation matches the text.
2 tools
Listed in project docs. Your client may show a different list.
list_voicesBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
Node.js >= 14.0.0
INSTALLATION
Connect your client
The block needs a path only you can supply — the full path to the server file you built on your machine. Everything else in it is the project's own.
Server setup
Configuration file
JSON
{
"mcpServers": {
"say": {
"command": "node",
"args": [
"<YOUR_PATH_TO_SAY_MCP_SERVER>/build/index.js"
]
}
}
}npm
TERMINAL
npm install say-mcp-server
