Microsoft Azure AI Speech
Official Azure AI Speech REST operations for token issuance, synthesis, and transcription.
Connect this API to an AI agent Browse all specs
What you can do with Microsoft Azure AI Speech via MCP
Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.
| Method | Path | Operation | Description |
|---|---|---|---|
| POST | /sts/v1.0/issueToken |
issueToken | Issue speech token Method: POST Path: /sts/v1.0/issueToken |
| POST | /cognitiveservices/v1 |
synthesizeSpeech | Synthesize speech Method: POST Path: /cognitiveservices/v1 IMPORTANT: This function has 3 REQUIRED parameter(s) and 0 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Header Parameters: REQUIRED: - Content-Type: No description - X-Microsoft-OutputFormat: No description Request Body: REQUIRED: - body: Request body (application/ssml+xml) |
| POST | /speechtotext/transcriptions:transcribe |
transcribeAudio | Transcribe audio Method: POST Path: /speechtotext/transcriptions:transcribe IMPORTANT: This function has 3 REQUIRED parameter(s) and 0 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Query Parameters: REQUIRED: - api-version: No description Header Parameters: REQUIRED: - Content-Type: No description Request Body: REQUIRED: - file: File parameter from audio/* |
Usage guide
## Authentication Create an Azure AI Speech resource and obtain its key and region. Send `Ocp-Apim-Subscription-Key: $AZURE_SPEECH_KEY` directly, or call `POST /sts/v1.0/issueToken` to obtain a short-lived bearer token and send `Authorization: Bearer $AZURE_SPEECH_TOKEN`. ## Text to speech Call `/cognitiveservices/v1` with well-formed SSML and `X-Microsoft-OutputFormat`. ## Speech to text Call `/speechtotext/transcriptions:transcribe` with `api-version` and an audio body on the server matching your region. Official docs: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech and https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text
How to use this spec
- Create a free VX Agents account (sandbox tools included).
- Open the marketplace and connect “Microsoft Azure AI Speech” to an agent.
- Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.