mcp-stt-azure mcp

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

Speech-to-text via Azure Cognitive Services Speech REST API. Auth via apiKey or AZURE_SPEECH_KEY env var. Region via baseUrl or AZURE_SPEECH_REGION env var.

sttazurespeechtranscriptioncognitive

Input Parameters

Parameter	Type	Description
filePathrequired	string	Path to the audio file (mp3, wav, ogg, m4a, flac, 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). Azure STT does not support translate. Default: `transcribe`.
promptoptional	string	Unused for Azure STT.
modeloptional	string	Unused — Azure uses region to select model.
apiKeyoptional	string	Azure Speech subscription key (or AZURE_SPEECH_KEY env var).
baseUrloptional	string	Region URL: https://{region}.stt.speech.microsoft.com (or set AZURE_SPEECH_REGION env var). Default: `https://eastus.stt.speech.microsoft.com`.

Output Fields

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

Examples

Transcribe call recording with Azure

// Input
{
  "filePath": "C:\\audio\\call.wav",
  "language": "en-US",
  "apiKey": "...",
  "baseUrl": "https://eastus.stt.speech.microsoft.com"
}

// Output
{
  "text": "Thank you for calling support.",
  "language": "en-US",
  "duration": 0
}

Install & Discovery

Install

ppm install mcp-stt-azure

Get JSON Schema

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

Discover by keyword

GET /v1/mcp/discover?q=stt

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