ElevenLabs MCP can now generate voice, music, images & video

ElevenLabs has added its ElevenCreative generation tools to the ElevenLabs MCP, giving Claude, ChatGPT and Cursor access to over 50 models.

· 2 min read
ElevenLabs

ElevenLabs has extended its hosted MCP server to ElevenCreative, the company's suite of generation tools, so an AI assistant can produce speech, music, sound effects, images, and video inside the conversation where the request is written. The update reaches Claude, ChatGPT, and Cursor through the same connector ElevenLabs already ships, with over 50 models reachable behind a single sign-in.

MCP is short for Model Context Protocol, an open standard that lets an assistant call outside services on a user's behalf. Until now, the ElevenLabs connector was scoped to ElevenAgents and covered management work: surfacing topics from recent conversations, duplicating an agent for a new market, comparing configurations across a workspace, and estimating expected model usage and cost before a change ships. Generation stayed in the ElevenLabs web app or behind the API. Creative tools now sit in the same tools list, so a script, a voiceover, a soundtrack, and a cover image can come out of one session without moving between applications.

0:00
/0:08

Installation runs on OAuth instead of API keys. In Claude, the connector installs from the connectors directory in a few clicks; Claude Code adds it from the terminal with a single command; ChatGPT takes it as a developer mode plugin; and Cursor accepts the server configuration in settings. Access is scoped to one ElevenLabs workspace and can be revoked from either the client or ElevenLabs account settings, with permissions ranging from read-only monitoring through to full agent management. A separate command-line path, installed via npm alongside a set of companion skills, covers coding agents including Codex, Claude Code, OpenClaw and Hermes.

ElevenCreative is the name ElevenLabs gave its generation products when it grouped them under one brand earlier this year. It covers text-to-speech, speech-to-text, voice changer, voice cloning, voice isolation, sound effects, music, voice design, the Studio editor for long-form projects, the Ads Engine, and the image and video generators. The original ElevenLabs MCP server from 2025, which runs locally on a developer machine with a user-supplied API key, remains available for developer workflows alongside the hosted version.

SPONSORED

Test ElevenLabs MCP yourself!

Learn more

ElevenLabs was founded in 2022 by Piotr Dabkowski and Mati Staniszewski and built its name on speech synthesis and dubbing before separating its products into three lines: ElevenCreative for generation, ElevenAgents for voice and chat agents, and ElevenAPI for direct programmatic access. The hosted connector arrived in August with agent management only, and this release closes the gap between the two halves of the product range. Adding generation to an assistant's tool list is a bet that production will shift toward the writing surface, where an audio or video asset is made during drafting instead of commissioned once a script is finished.