// MCP TOOL REFERENCE

SPEECH MCP TOOLS

7 tools from the Speech MCP MCP Server, categorised by risk level.

View the Speech MCP policy →

// ALL 7 SPEECH MCP TOOLS

READ 1 tools

Read transcribe Transcribe an audio or video file to text. This tool uses faster-whisper to transcribe speech from...

WRITE 1 tools

Write narrate Convert text to speech and save as an audio file. This will use the configured TTS engine to gener...

EXECUTE 5 tools

Execute launch_ui Launch the speech UI. This will start the speech UI window that shows the microphone status and sp... Execute narrate_conversation narrate_conversation Execute reply Speak the provided text and optionally listen for a response. This will speak the given text and t... Execute start_conversation Start a voice conversation by beginning to listen. This will initialize the speech recognition sys... Execute close_ui Close the speech UI window. This will gracefully shut down the speech UI window if it's currently ...

// FAQ

How many tools does the Speech MCP MCP server have? +

The Speech MCP MCP server exposes 7 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Speech MCP tools? +

Route the Speech MCP server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Speech MCP tools fall into? +

Speech MCP tools are categorised as Read (1), Write (1), Execute (5). Each category has a recommended default policy.

Enforce policy on every Speech MCP tool call.

Start from Speech MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.