speech_to_speech · ElevenLabs MCP: Risk & Policy

WHAT IT DOES

What speech_to_speech does on ElevenLabs

AI agents invoke speech_to_speech to trigger actions in ElevenLabs. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why speech_to_speech needs a policy

Speech-to-speech conversion executes an external AI/audio processing operation whose effects depend on the provided arguments (source audio, target voice selection, emotional parameters). While it doesn't delete data or handle financial transactions, it triggers execution of complex audio processing pipelines.

From the tool's definition Tool 'speech_to_speech' performs voice transformation on audio files, converting input audio to use a different voice. This is an external operation that produces audio output based on provided arguments (input audio and target voice parameters).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

speech_to_speech Rate-limited

speech_to_speech stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "speech_to_speech": {
      "limits": [
        {
          "counter": "speech_to_speech_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ElevenLabs, so you can run agents against it safely.

FAQ

Questions about speech_to_speech

What does the speech_to_speech tool do? +

Transform audio to use a different voice while preserving emotion and cadence. Trigger:. It is categorised as a Execute tool in the ElevenLabs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on speech_to_speech? +

Register the ElevenLabs MCP server in PolicyLayer and add a rule for speech_to_speech: 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 ElevenLabs. Nothing to install.

What risk level is speech_to_speech? +

speech_to_speech is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit speech_to_speech? +

Yes. Add a rate_limit block to the speech_to_speech 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.

How do I block speech_to_speech completely? +

Set action: deny in the PolicyLayer policy for speech_to_speech. 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.

What MCP server provides speech_to_speech? +

speech_to_speech is provided by the ElevenLabs MCP server (wynandw87/claude-code-elevenlabs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.