The official Elevenlabs MCP Server
Give Claude and Cursor access to the entire ElevenLabs AI audio platform via simple text prompts. You can even spin up voice agents to perform outbound calls for you — like ordering pizza.
Elevenlabs MCP enables MCP clients like Claude Desktop to call ElevenLabs Text-to-Speech APIs directly, allowing AI agents to produce high-quality audio output without leaving the agent environment. Users can generate speech, clone voices, and process audio as part of multi-step agent tasks.
The MCP server bridges ElevenLabs APIs to MCP clients through standardized tools. Developers configure the server with an API key and immediately gain access to voice generation, voice cloning, audio transcription, and audio isolation features within their preferred AI development environment.
Elevenlabs MCP provides voice design and voice cloning tools that allow agents to generate speech variations and create unique voice profiles. Users can design voices matching specific character traits or clone existing voices for consistent agent personalities across conversations.
The MCP server exposes ElevenLabs audio isolation and transcription capabilities, enabling developers to build workflows that convert speech to text, identify speakers, and apply voice transformations—all orchestrated through MCP client interfaces without manual API calls.