mcp-tts-openai mcp

v1.0.1 · MCP Tool · audio · registry.pascalai.org

Text-to-speech via OpenAI TTS API (tts-1 / tts-1-hd). Returns base64-encoded audio or saves to file. Auth via apiKey param or OPENAI_API_KEY env var.

ttsopenaitext-to-speechaudiospeech

Input Parameters

Parameter	Type	Description
textrequired	string	Text to convert to speech. Max ~4096 characters.
voiceoptional	string	Voice: alloy, echo, fable, onyx, nova (default), shimmer. Default: `nova`.
modeloptional	string	TTS model: tts-1 (default, faster), tts-1-hd (higher quality). Default: `tts-1`.
output_pathoptional	string	Save audio to this file path (e.g. C:\speech.mp3). Auto-generates temp file if empty.
speedoptional	number	Playback speed 0.25–4.0. Default: 1.0. Default: `1.0`.
formatoptional	string	Output format: mp3 (default), wav, opus, aac. Default: `mp3`.
apiKeyoptional	string	OpenAI API key (or OPENAI_API_KEY env var).

Output Fields

Field	Type	Description
ok	boolean
audio	string	Base64-encoded audio (when outputPath not set).
output_path	string	File path where audio was saved.
format	string
size	integer
error	string

Examples

Convert text to speech (base64)

// Input
{
  "text": "Hello! Welcome to our AI-powered assistant. How can I help you today?",
  "voice": "nova",
  "model": "tts-1-hd",
  "apiKey": "sk-..."
}

// Output
{
  "ok": true,
  "audio": "//NExAA...",
  "format": "mp3",
  "size": 48320
}

Save speech to file

// Input
{
  "text": "Your order has been shipped and will arrive tomorrow.",
  "voice": "alloy",
  "apiKey": "sk-...",
  "outputPath": "C:\\audio\\order.mp3"
}

// Output
{
  "ok": true,
  "outputPath": "C:\\audio\\order.mp3",
  "format": "mp3",
  "size": 32000
}

Install & Discovery

Install

ppm install mcp-tts-openai

Get JSON Schema

GET /v1/packages/mcp-tts-openai/1.0.1/schema

Discover by keyword

GET /v1/mcp/discover?q=tts

Discovery hint: Install with ppm install mcp-tts-openai or invoke remotely via POST /v1/invoke/mcp-tts-openai on the MCP Service.