text_to_speechLABSCO SUMMARY
Check the model status before you conclude it is broken.
The first launch downloads and initialises the model, and a synthesis request during that window looks like a failure rather than a wait — which is exactly why there is a status tool reporting elapsed time and retry count. Once the weights are cached, the whole path is local: no key, no upload, no per-character cost.
What it is
A local speech server. The Kokoro model is downloaded and initialised on first start and then does the synthesis on your machine, so text never goes to a speech vendor and there is nothing to bill per character.
What you get
- Text converted to speech with the default settings, optionally naming a voice —
text_to_speech - The same with a speed multiplier between 0.5 and 2.0 —
text_to_speech_with_options - Every available voice listed —
list_voices - The model's initialisation state, which matters on first start while the weights download:
uninitialized,initializing,readyorerror, with retry information included —get_model_status
Requirements
No API key. Node.js, since it is launched with npx -y speech-mcp-server; the package is speech-mcp-server (1.1.2). Two optional environment variables set the defaults: MCP_DEFAULT_SPEECH_SPEED, which defaults to 1.1 and accepts 0.5 to 2.0, and MCP_DEFAULT_VOICE, which defaults to af_bella. The model downloads itself on first launch and the server retries initialisation up to 3 times with a cleanup between attempts.
Setup effort
One command — npm install speech-mcp-server
USE CASES
01
Hearing a draft read back
Convert the text you are working on to speech to catch phrasing that reads fine but sounds wrong.
02
Choosing a voice for a project
List the available voices and try the same line in several before settling on one.
03
Getting the pacing right
Adjust the speed multiplier per request rather than accepting the default rate.
04
Keeping the text on your own machine
Synthesise material you would not send to a hosted speech API — the model runs locally and no key is involved.
4 tools
Listed in project docs. Your client may show a different list.
text_to_speech_with_optionslist_voicesget_model_statusBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
npx on PATH
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install speech-mcp-serverMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"speech": {
"command": "npx",
"args": [
"-y",
"speech-mcp-server"
],
"env": {
"MCP_DEFAULT_SPEECH_SPEED": "1.3",
"MCP_DEFAULT_VOICE": "af_bella"
}
}
}
}Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"speech": {
"command": "npx",
"args": [
"-y",
"speech-mcp-server"
]
}
}
}
