mcp-stt-google mcp

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

Speech-to-text via Google Cloud Speech-to-Text REST API v1. Models: latest_long, latest_short, telephony, medical_dictation. Auth via apiKey, GOOGLE_API_KEY or GEMINI_API_KEY env var.

sttgooglespeechtranscriptioncloud

Input Parameters

Parameter	Type	Description
filePathrequired	string	Path to the audio file (mp3, wav, flac, ogg, webm).
languageoptional	string	Language code BCP-47 (e.g. es-ES, en-US, fr-FR). Default: en-US. Default: `en-US`.
operationoptional	string	Operation: transcribe (default). Google STT does not support translate. Default: `transcribe`.
promptoptional	string	Context phrase hints for better accuracy.
modeloptional	string	Model: latest_long (default), latest_short, telephony, medical_dictation. Default: `latest_long`.
apiKeyoptional	string	Google Cloud API key (or GOOGLE_API_KEY / GEMINI_API_KEY env var).
baseUrloptional	string	Base URL override (default: https://speech.googleapis.com). Default: `https://speech.googleapis.com`.

Output Fields

Field	Type	Description
text	string	Transcribed text.
language	string
duration	number
confidence	number
operation	string
error	string

Examples

Transcribe audio with Google Cloud STT

// Input
{
  "filePath": "C:\\audio\\podcast.mp3",
  "language": "en-US",
  "model": "latest_long",
  "apiKey": "AIza..."
}

// Output
{
  "text": "Welcome to today's episode.",
  "language": "en-US",
  "confidence": 0.97
}

Install & Discovery

Install

ppm install mcp-stt-google

Get JSON Schema

GET /v1/packages/mcp-stt-google/1.0.1/schema

Discover by keyword

GET /v1/mcp/discover?q=stt

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