Converts a local audio file's spoken dialogue directly into structured text.
AI agents call speech_to_text to retrieve information from MCP Audio Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and processes an audio file to extract its content (transcription) but does not modify, delete, execute code, move money, or trigger external state changes. It is purely informational/analytical in nature, making it a Read-category tool with low severity.
From the tool's definition Tool 'speech_to_text' converts audio to text—a retrieval and transformation operation with no side effects on the audio file or external systems. Description explicitly states 'converts...directly into structured text', indicating data extraction only.
Attacks that exploit this kind of access
Converts a local audio file's spoken dialogue directly into structured text. It is categorised as a Read tool in the MCP Audio Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Audio Server MCP server in PolicyLayer and add a rule for speech_to_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Audio Server. Nothing to install.
speech_to_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the speech_to_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for speech_to_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
speech_to_text is provided by the MCP Audio Server MCP server (thrid3v/speechtotext-fastmcp-n8n-workflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →