Log inSubmit server
ElevenLabs logo

ElevenLabs

Connects AI clients to ElevenLabs for speech, voice, music, dubbing, pronunciation, history, and account operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install ElevenLabs

Pick your client, then add it in one click or paste the config.

SSE (Remote)
Server URL
https://api.mcp.ai/p_elevenlabs

Remote servers are added in the app, not the config file: Customize → Connectors → Add custom connector, then paste this URL.

Overview

The ElevenLabs MCP server connects AI clients to the ElevenLabs API through MCP over HTTP. It exposes 149 tools for text-to-speech, voice creation and management, dialogue, sound generation, dubbing, pronunciation dictionaries, Studio projects, history, and account information. Use it when an agent needs to generate or manage ElevenLabs audio with natural-language requests. Requests use the connected ElevenLabs account, and generated audio consumes credits from that subscription.

Use cases

  • Generate speech from text with a selected ElevenLabs voice
  • Manage voices and adjust their settings
  • Retrieve or download generated audio from speech history
  • Create multi-voice dialogue, podcasts, or sound effects
  • Inspect subscription details and remaining account credits

Key features

  • Text-to-speech and multi-voice dialogue generation
  • Voice creation, design, remixing, and management
  • Speech history retrieval, download, and deletion
  • Sound effects, podcasts, dubbing, and pronunciation dictionaries
  • ElevenLabs Studio project and chapter management
  • User and subscription information access

Tools155

What ElevenLabs lets your agent do. Expand a tool for its parameters.

Verified live~32.2k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

7/13 checks healthy over the last 40d

What it can do

From the 155 tools this server returned when we ran it.

Can delete or modify data · 23Handles credentials · 12Makes network requests · 12Read-only tools · 132

Observed 2026-10-16 in an isolated sandbox. A description of reach, not a security audit.

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit1mo agoMost recent push to the default branch.
Tools exposed155Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How ElevenLabs works

What the ElevenLabs MCP server does

The ElevenLabs MCP server gives MCP-compatible AI clients access to ElevenLabs operations through natural-language instructions. It covers both audio generation and account or content management, with 149 tools listed by the project.

Typical requests include listing available voices, generating speech with a selected voice, checking remaining credits, retrieving generated audio, and managing voice settings. The available operations also extend to dialogue with multiple voices, sound effects, voice design, voice remixing, podcasts, dubbing, pronunciation dictionaries, and ElevenLabs Studio projects.

The server supports reading and writing actions. That means an agent can not only inspect voices, history, projects, and subscription details, but can also create, update, convert, or delete supported resources.

How it works

The ElevenLabs MCP server is exposed through an MCP-over-HTTP endpoint rather than requiring a local process in the documented installation flow. The endpoint supplied by the project is:

https://api.mcp.ai/p_elevenlabs

An MCP client sends tool calls to that endpoint, and the server performs the corresponding action against ElevenLabs. Authentication uses the user’s own ElevenLabs API key, while the project also documents magic-link login without a password. Audio-generation charges are applied to the connected ElevenLabs subscription.

Tool calls can include operations such as selecting a voice, generating speech, retrieving a history item, or changing voice settings. Several listed tools support bulk inputs, including batches of history items, voices, samples, projects, or other resource identifiers.

Setup and configuration

Add the HTTP endpoint to an MCP client that supports MCP over HTTP. The README provides one-click installation links or instructions for Claude Web and Desktop, Cursor, and VS Code with Copilot Chat. Other clients can use the same URL when they support MCP over HTTP.

The documented client names include Claude Desktop, Cursor, VS Code, Cline, and Continue. After connecting, authenticate with the ElevenLabs account and authorize use of its API key.

Tools and capabilities

The ElevenLabs MCP server includes tools for:

  • Converting text to speech, including full audio generation and multi-voice dialogue.
  • Generating sound effects and creating or remixing voice designs.
  • Listing, inspecting, updating, sharing, replicating, and deleting voices.
  • Reading and changing voice settings, including default and voice-specific settings.
  • Managing speech history, including retrieval, download, audio access, and deletion.
  • Creating podcasts and working with dubbing, pronunciation dictionaries, and audio isolation history.
  • Listing, editing, converting, snapshotting, and deleting Studio projects and chapters.
  • Reading user, subscription, and usage-related account information.

Some endpoints return audio directly, while voice-design operations can return previews with generated voice identifiers and base64-encoded MP3 samples.

Limitations and notes

Music and sound-effect generations are not included in the retrievable speech-history API described by the project. The standard voice-listing operation stops working when a workspace exceeds 500 voices; the V2 voice listing provides search, filtering, and pagination instead.

The server depends on the connected ElevenLabs account and its subscription credits. Audio generation is therefore not independent of ElevenLabs billing or account limits.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about ElevenLabs

ElevenLabs is an MCP server that connects AI clients to the ElevenLabs API through MCP over HTTP. Its main tools generate speech, create and manage voices, produce dialogue and sound effects, manage dubbing and Studio projects, retrieve audio history, and read account or subscription information.

Install it by adding https://api.mcp.ai/p_elevenlabs as an MCP-over-HTTP server in your client. The project provides one-click options for Claude, Cursor, and VS Code, and says the same endpoint works with other clients that support MCP over HTTP.

Yes, ElevenLabs works with Cursor through the documented MCP installation link or by adding its HTTP endpoint manually. After connecting, use the ElevenLabs account and API key associated with the server to make speech, voice, and account-related tool calls.

Yes, it can retrieve audio from speech-history items and download one or more history items. The documented history API does not include music or sound-effect generations, so those outputs cannot currently be retrieved through the speech-history tools.

Related MCP servers

All in Text-to-Speech All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewElevenLabs AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/elevenlabs?style=directory)](https://allmcps.com/mcp/elevenlabs)
HTML Embed
<a href="https://allmcps.com/mcp/elevenlabs"><img src="https://allmcps.com/api/badge/elevenlabs?style=directory" alt="ElevenLabs on AllMCPs" /></a>