mcp-tts mcp

v1.1.0 · MCP Tool · audio · registry.pascalai.org

Text-to-speech via OpenAI TTS API (tts-1 / tts-1-hd). Converts text to audio and returns base64-encoded audio data. Auth via apiKey param or OPENAI_API_KEY env var.

ttstext-to-speechopenaiaudiospeech

Input Parameters

ParameterTypeDescription
textrequired string Text to convert to speech. Max ~4000 characters per request.
voiceoptional string Voice: alloy, echo, fable, onyx, nova (default), shimmer. Default: nova.
provideroptional string Provider: openai (default), auto. Default: openai.
modeloptional string TTS model: tts-1 (default, faster), tts-1-hd (higher quality). Default: tts-1.
formatoptional string Output format: mp3 (default), wav, opus, aac. Default: mp3.
speedoptional number Playback speed 0.25-4.0. Default: 1.0. Default: 1.0.
apiKeyoptional string OpenAI API key (or OPENAI_API_KEY env var).

Output Fields

FieldTypeDescription
ok boolean
audio string Base64-encoded audio data.
format string
size integer
error string

Examples

Convert text to speech (mp3)

// Input
{
  "text": "Hello, this is a test.",
  "voice": "nova",
  "apiKey": "sk-..."
}

// Output
{
  "ok": true,
  "audio": "//NExAA...",
  "format": "mp3",
  "size": 12800
}

Install & Discovery

Install

ppm install mcp-tts

Get JSON Schema

GET /v1/packages/mcp-tts/1.1.0/schema

Discover by keyword

GET /v1/mcp/discover?q=tts
Discovery hint: Install with ppm install mcp-tts or invoke remotely via POST /v1/invoke/mcp-tts on the MCP Service.