ElevenLabs
Free集成 ElevenLabs TTS API，能生成包含多种声音的完整画外音。
FreeFree tier
Inputs: textOutputs: audio
About ElevenLabs
ElevenLabs MCP Server is a Model Context Protocol (MCP) server that integrates with the ElevenLabs text-to-speech API. It provides tools for generating audio from plain text or structured scripts with multiple voices and actors, managing voiceover job history via SQLite, and listing available voices. The project includes a sample SvelteKit web-based MCP client for simple TTS conversion, multi-part script management, voice history tracking, playback, and audio file downloads. It is open-source under the MIT license and can be installed easily via uvx or Smithery.
Key Features
Generate audio from text using ElevenLabs API
Support for multiple voices and script parts (actors/voice lines)
SQLite database for persistent job and history storage
Sample SvelteKit MCP Client for text-to-speech, script management, history tracking, and file downloads
Tools: generate_audio_simple, generate_audio_script, delete_job, get_audio_file, list_voices, get_voiceover_history
Resources: voiceover://history/{job_id} and voiceover://voices
Pros & Cons
Pros
- Open-source with MIT license
- Easy installation via uvx (no manual setup)
- Includes a functional web-based UI (SvelteKit) for testing and playback
- Supports multiple voices and script parts for complex audio projects
- Persistent history stored in SQLite for tracking past generations
Cons
- Requires an ElevenLabs API key (external paid service)
- No built-in audio editing capabilities
- No official releases or packaged binaries; relies on running from source or uvx
Best For
Convert plain text into spoken audio using ElevenLabs voicesCreate narrated scripts with multiple voices for videos or presentationsManage and review voiceover job history with persistent storageBuild AI assistants that can generate and retrieve audio via MCP
FAQ
What is ElevenLabs MCP Server?
It is an MCP (Model Context Protocol) server that provides tools to generate audio using the ElevenLabs text-to-speech API, with support for multiple voices, script parts, and history tracking.
How do I install it?
You can install it using uvx (run 'uvx elevenlabs-mcp-server') or via Smithery. Alternatively, clone the repository, set up a virtual environment with uv, and configure environment variables like ELEVENLABS_API_KEY.
What tools are available?
The server provides six tools: generate_audio_simple, generate_audio_script, delete_job, get_audio_file, list_voices, and get_voiceover_history.
Is there a user interface?
Yes, the repository includes a sample SvelteKit web client located in clients/web-ui that allows you to run TTS conversion, manage scripts, and play back audio.