audio_isolation
Audio Isolation. Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
This record as markdown: /tools/aiwerk-mcp-server-elevenlabs/audio-isolation.md
What audio_isolation does on Elevenlabs
AI agents use audio_isolation to create or update resources in Elevenlabs, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Elevenlabs environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
audio_path | string | — | The audio file from which vocals/speech will be isolated from. Local path. Required for this call. |
file_format | object | — | The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel ( |
output_path | string | — | Where to write the returned bytes. Relative paths resolve against ELEVENLABS_OUTPUT_DIR. Omit it to get the data inline as base64 (small files only). |
preview_b64 | string | null | — | Optional preview image base64 for tracking this generation. |
audio_base64 | string | — | Base64 contents for "audio". Use this when the server cannot read your local disk. |
audio_filename | string | — | Filename to send for "audio". Some endpoints infer the audio format from it. |
Parameters from the server's own tool schema.
Why audio_isolation is rated Medium
An AI agent can call audio_isolation faster than any human can review: one bad instruction and it creates or modifies resources in Elevenlabs by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs audio_isolation safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Elevenlabs, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For audio_isolation, this is the rule to start with:
audio_isolation stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Elevenlabs, apply this rule, and every audio_isolation call is checked against it from then on.
Questions about audio_isolation
Audio Isolation. Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them. It is categorised as a Write tool in the Elevenlabs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
audio_isolation accepts 6 parameters: audio_path, file_format, output_path, preview_b64, audio_base64, audio_filename. The full parameter table on this page comes from the server's own tool schema.
Register the Elevenlabs MCP server in PolicyLayer and add a rule for audio_isolation: 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.
audio_isolation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the audio_isolation 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 audio_isolation. 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.
audio_isolation is provided by the Elevenlabs MCP server (@aiwerk/mcp-server-elevenlabs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Elevenlabs, and thousands of servers like it.
This server
Across the catalogue