ElevenLabs MCP Adds Voice, Music, Image, and Video Generation
By Steven Van ·
ElevenLabs adds speech, transcripts, dubs, music, sound effects, image, and video generation to its MCP so you can create media from your assistant.
ElevenLabs has introduced voice, music, image, and video generation in the ElevenLabs MCP, so you can generate media from the assistant you already work in.
Until now the ElevenLabs MCP was pitched mainly at managing voice and chat agents from an assistant. This update extends it to the creative side of the platform, covering speech, transcripts, dubs, music, sound effects, images, and video without leaving your assistant.
- Generate speech and transcripts directly from an MCP-connected assistant.
- Create dubs of existing content.
- Generate music and sound effects.
- Generate images and video through the same MCP.
- Everything runs from the assistant you already use, with no separate app to open.
The full list of generation types is in the announcement.
ElevenLabs
AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.
View ElevenLabs →