text-to-speech
Converts text to speech and plays it using OpenAI's TTS API
LABSCO SUMMARY
It plays the audio rather than handing you a file, and that single fact decides where this server is useful.
The one tool converts the text and plays it through the machine running the server, so the output lands wherever that machine's audio goes rather than in the conversation. That makes it a read-aloud and notification tool rather than an audio-production one. The instructions parameter is the part worth using — alongside speed it lets the delivery be directed instead of accepted — while the voice and model are chosen when the server is started rather than per call.
What it is
A single-tool text-to-speech server that converts text through OpenAI's TTS API and plays the result.
What you get
- One call with delivery control: text-to-speech takes the text, a speed and instructions for how it should be spoken, converts it through OpenAI's TTS API and plays it.
Requirements
An OpenAI API key, supplied as OPENAI_API_KEY, and audio output on the machine running the server, since the tool plays the speech rather than returning a file.
Setup effort
One command plus a key — npx tts-mcp tts-mcp-server --voice nova --model tts-1-hd, then supply credentials
USE CASES
01
Hearing a long answer instead of reading it
Send the text with a speed and delivery instructions and let the machine speak it.
02
Getting an audible cue when a long task finishes
Speak a short line at the end of the run so the result reaches you away from the screen.
1 tool
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool when we connected. Speech plays through your speakers; saving to a file is only in the tts-mcp command-line tool. --voice, --model and --format are fixed when the server starts.
Requires
- npx on PATH
- OPENAI_API_KEY in your environment
Where it runs
Both documented setups run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
Server setup
TERMINAL
npx tts-mcp tts-mcp-server --voice nova --model tts-1-hdMCP Clients
Claude Desktop — npx
CLAUDE DESKTOP — NPX · JSON
{
"mcpServers": {
"tts-mcp": {
"command": "npx",
"args": [
"-p",
"tts-mcp",
"tts-mcp-server",
"--voice",
"nova",
"--model",
"gpt-4o-mini-tts"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Claude Desktop — Local build
CLAUDE DESKTOP — LOCAL BUILD · JSON
{
"mcpServers": {
"tts-mcp": {
"command": "node",
"args": [
"<YOUR_PATH_TO_BIN>/tts-mcp-server.js",
"--voice",
"nova",
"--api-key",
"<YOUR_OPENAI_API_KEY>"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}
