Labsco
MCP SERVER

Text-to-Speech MCP

by nakamurau1 ↗

Speak a piece of text aloud through OpenAI's text-to-speech, with the delivery directed rather than left to the default.

Speech Synthesis & Transcription✓ Verified
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