mcpSource-backedReview first Safety ✓ Privacy ✓

ElevenLabs MCP Server

Official ElevenLabs MCP server for generating speech, designing voices, cloning voices, transcribing audio, creating sound effects, and working with conversational audio agents through the ElevenLabs API.

by ElevenLabs·added 2026-06-06·

Claude CodeClaude Desktop

HarnessClaude CodeClaude Desktop

Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

ElevenLabs MCP Server can call paid ElevenLabs API endpoints; text-to-speech, voice design, voice cloning, audio isolation, transcription, sound generation, music, and agent workflows can consume account credits.
Voice cloning and voice conversion can create realistic synthetic speech, so require documented consent and review before processing a person's voice or publishing generated audio.
Generated speech, sound effects, music, transcripts, and conversation-agent configuration can affect public-facing content; review prompts, voice IDs, output format, language, and destination before publishing or sending.
File output mode writes generated files to disk under the configured base path; restrict that path to an approved directory and avoid broad home, desktop, or shared folders in production.
Use separate API keys or workspaces for test and production clients, monitor credit usage, and disable tools in clients that should not spend credits.
Some operations may take longer than normal MCP tool timeouts; do not retry expensive generation calls blindly.

Privacy notes

The MCP client can expose ElevenLabs API keys, voice IDs, text prompts, voice descriptions, uploaded audio samples, generated audio paths, transcripts, diarized speaker labels, and conversational-agent settings.
Uploaded audio and generated outputs may contain biometric voice characteristics, names, background sounds, private conversations, or copyrighted material.
File, resource, and both output modes can retain generated audio locally, in MCP resources, in logs, or in chat transcripts depending on the client.
Treat voice samples and transcripts as sensitive data, and delete generated files or cached resources when they are no longer needed.
Review ElevenLabs account, retention, residency, and enterprise data-residency settings before using the server with regulated or customer data.

Prerequisites

Python 3.11 or newer with `uvx` available.
An ElevenLabs API key for the account and workspace you intend Claude to use.
Review of ElevenLabs pricing, credits, voice-cloning policy, content rules, and data handling before enabling tools that generate or process audio.
An approved output directory when using file-based generated audio output.
Explicit consent and rights for any voice samples, transcripts, music, sound effects, or conversational-agent content processed through the server.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 10 minutes
Difficulty: intermediate

Tool listing metadata

Disclosure: Official ElevenLabs MCP server published as the `elevenlabs-mcp` Python package under the MIT license; API usage requires an ElevenLabs account and may consume paid credits.

Full copyable content

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "YOUR_ELEVENLABS_API_KEY",
        "ELEVENLABS_MCP_BASE_PATH": "/path/to/approved/audio-output",
        "ELEVENLABS_MCP_OUTPUT_MODE": "files"
      }
    }
  }
}

About this resource

Content

ElevenLabs MCP Server is the official MCP integration for using ElevenLabs audio APIs from Claude and other MCP clients. It exposes tools for text-to-speech, voice design, voice cloning, transcription, audio isolation, sound generation, music generation, and conversational audio-agent workflows.

Use it when Claude needs supervised access to generate or transform audio while keeping API-key configuration, output-file handling, voice consent, and credit usage visible to the operator.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, license, package manifest, official MCP server manifest, agent context, server entrypoint, conversational-agent helper, and file-output utilities for current setup and behavior details.

Features

Generate speech from text with ElevenLabs voices and model settings.
Create or select voices by name or ID.
Design new voices from text descriptions.
Clone or convert voices from approved audio samples.
Transcribe audio and format diarized speaker output.
Generate sound effects, soundscapes, and music through ElevenLabs APIs.
Create and configure conversational audio agents.
Save generated files to disk, return generated data as MCP resources, or use both output modes.
Configure optional API residency and base output paths through environment variables.

Installation

Create an ElevenLabs API key, then configure your MCP client with the published Python package:

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "YOUR_ELEVENLABS_API_KEY",
        "ELEVENLABS_MCP_BASE_PATH": "/path/to/approved/audio-output",
        "ELEVENLABS_MCP_OUTPUT_MODE": "files"
      }
    }
  }
}

Claude Code users can add it with:

claude mcp add elevenlabs --env ELEVENLABS_API_KEY=YOUR_ELEVENLABS_API_KEY -- uvx elevenlabs-mcp

Use ELEVENLABS_MCP_OUTPUT_MODE=resources when the client should receive generated files as MCP resources instead of writing them to disk, or both when you need both local files and resource access.

Use Cases

Generate narrated speech for a prototype, lesson, game, or accessibility workflow.
Produce multiple voice variations for review before adding one to a voice library.
Convert approved voice samples into a different voice style.
Transcribe audio and identify speakers for supervised review.
Create sound effects or soundscapes from text prompts.
Configure a conversational audio agent with a specific voice and prompt.
Compare output formats, models, and latency/cost tradeoffs before publishing audio.

Safety and Privacy

ElevenLabs MCP Server can spend API credits and create realistic synthetic audio. Keep human approval in front of voice cloning, public release, customer communications, or any workflow involving another person's voice.

Set ELEVENLABS_MCP_BASE_PATH to an approved directory before using file output mode. Generated audio, transcripts, and conversation-agent files can persist on disk or in MCP resources, so clean up outputs and logs according to your data retention policy.

#elevenlabs#text-to-speech#audio#voice#transcription

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.