Transcribe an audio file URL to text (wav, mp3, m4a, ogg/opus, flac, webm; ≤15 MB, ≤15 minutes — split longer recordings). Returns punctuated transcript, confidence, duration, detected language, word-level timestamps, and (diarize=true) speaker-segmented utterances.
AI agents call transcribe.audio to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and transforms audio input into text output (transcription). It does not create, modify, delete, execute code, or move money. The output is informational only. The payment model (pay-per-call in USDC) is a billing mechanism external to the tool's function and does not change its classification.
From the tool's definition Tool transcribes audio files to text and returns transcript, confidence, duration, language, and timestamps — a data retrieval operation with no side effects, no modifications, no execution, and no destructive actions.
Attacks that exploit this kind of access
Transcribe an audio file URL to text (wav, mp3, m4a, ogg/opus, flac, webm; ≤15 MB, ≤15 minutes — split longer recordings). Returns punctuated transcript, confidence, duration, detected language, word-level timestamps, and (diarize=true) speaker-segmented utterances. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for transcribe.audio: 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. Nothing to install.
transcribe.audio 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 transcribe.audio 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 transcribe.audio. 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.
transcribe.audio is provided by the MCP server (@2sio/mcp). 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 →