speakLABSCO SUMMARY
Speech that never leaves the machine.
No API key and no cloud call: the model is fetched once and everything after that is local, which makes it usable on text you would not hand to a hosted service. Voices and expression tags are enumerable, so the assistant can pick one rather than being told which to use.
What it is
A local text-to-speech server powered by Supertonic 3, running over stdio. Synthesis happens on your own machine; the model downloads once into a cache and works offline after that.
What you get
- Text synthesised to a WAV file, returned as an absolute path with its metadata
- Built-in voices listed with their IDs and gender
- Inline expression tags - laugh, breath and others - listed with descriptions, usable inside the text
- A language set per call, so non-English text is spoken correctly rather than read as English
- Optional playback on the machine running the server, on macOS and Linux
- Offline operation after a preload step that downloads the weights and prints their checksums
Requirements
Python and a virtual environment, installed from a checkout. Playback and synthesis output paths cover macOS and Linux; Windows is not supported in the current version. The first start downloads the model unless you preload it.
Setup effort
Build from source — git clone https://github.com/Halozen-Inc/supertonic3-mcp && cd supertonic3-mcp
USE CASES
01
Producing audio without sending the text anywhere
Synthesis runs on your own machine and writes a WAV file locally, so confidential copy never reaches a third-party service.
02
Choosing the voice before you generate
Read the built-in voices with their IDs and gender, and pick one deliberately instead of accepting the default.
03
Adding laughs and breaths to a synthesised line
List the inline expression tags with their descriptions, then place them in the text where the delivery needs them.
04
Speaking text that is not in English
Set the language explicitly on the call, so the pronunciation follows the actual language rather than the English default.
3 tools
Listed in project docs. Your client may show a different list.
list_voiceslist_expressionsBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
Python 3.10+
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/Halozen-Inc/supertonic3-mcp && cd supertonic3-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"MCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"supertonic3": {
"command": "<YOUR_PATH_TO_SUPERTONIC3_MCP>/.venv/bin/supertonic3-mcp",
"args": []
}
}
}<YOUR_PATH_TO_SUPERTONIC3_MCP> is the full path of the folder the clone step created. The README's own block says supertonic-tts here, but the clone creates supertonic3-mcp. The first start downloads the model into ~/.cache/supertonic3/ unless you ran supertonic3-mcp preload first.
