広告掲載
MCP.so
ログイン

Elevenlabs MCP Server

@elevenlabs

リポジトリホームページ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

elevenlabs

Elevenlabs MCP Server について

The official ElevenLabs MCP server

#mcp#elevenlabs#elevenlabs-api

Elevenlabs MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "ElevenLabs": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
      }
    }
  }
}

Elevenlabs MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Elevenlabs Mcp?

Elevenlabs Mcp is the official ElevenLabs Model Context Protocol (MCP) server that enables interaction with Text to Speech and audio processing APIs. It allows MCP clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents to generate speech, clone voices, transcribe audio, and more.

How to use Elevenlabs Mcp?

Install with uvx elevenlabs-mcp or pip install elevenlabs-mcp, configure your ElevenLabs API key via the ELEVENLABS_API_KEY environment variable, and add the server config to your MCP client's configuration file (e.g., claude_desktop_config.json for Claude Desktop). Optionally set ELEVENLABS_MCP_BASE_PATH, ELEVENLABS_MCP_OUTPUT_MODE, and ELEVENLABS_API_RESIDENCY environment variables to customize file output and data residency.

Key features of Elevenlabs Mcp

  • Text to speech generation with multiple voice options
  • Voice cloning and voice library management
  • Audio transcription and speaker diarization
  • Sound effect and soundscape generation
  • Voice design for custom character voices
  • Audio isolation and conversion tools

Use cases of Elevenlabs Mcp

  • Generate natural-sounding speech from text for narratives or assistants
  • Clone a voice and apply it to new content or characters
  • Transcribe audio, identify different speakers, and re-voice each speaker
  • Create custom soundscapes like thunderstorms or jungle environments
  • Convert a voice recording to sound like a different character or style

よくある質問

1

What API key do I need and is there a free tier?

You need a valid ElevenLabs API key from the ElevenLabs app settings. There is a free tier with 10,000 credits per month.

2

What MCP clients are supported?

Supported clients include Claude Desktop, Cursor, Windsurf, and OpenAI Agents, as well as any MCP-compatible client.

3

How do I handle timeouts with certain tools?

Voice design and audio isolation can take a long time. Timeout errors may appear in the MCP inspector dev mode but should not occur with clients like Claude Desktop.

4

What output modes are available for generated files?

Three modes: `files` (save to disk and return paths), `resources` (return base64-encoded data as MCP resources), and `both` (save to disk and return as resources). Default is `files`.

5

Where are logs located when running with Claude Desktop?

On Windows at `%APPDATA%\Claude\logs\mcp-server-elevenlabs.log`, and on macOS at `~/Library/Logs/Claude/mcp-server-elevenlabs.log`.

コメント

「その他」の他のコンテンツ

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
広告掲載