ElevenLabs Integrates Voice, Music, and Video Generation via MCP Expansion

ElevenLabs has expanded its existing MCP (Model Context Protocol) connection to integrate voice, music, image, and video generation capabilities. Users can access over 50 models with a single OAuth login from supported AI assistants such as Claude, ChatGPT, and Cursor.

Integrated Creative Workflow

The new MCP connection allows users to generate and manage various media directly within the chat interface.

• Voice and Text Conversion: Convert text to speech, or convert audio files into transcripts with speaker labels and timestamps in 99 languages via Scribe.
• Dubbing and Music: Dub into other languages while preserving the original speaker's tone and delivery, or generate music and sound effects in specific genres.
• Image and Video: Perform image generation, editing, video animation, and lip-syncing within a single connector.

Workspace Integration and Security

All generated assets are stored in the ElevenCreative workspace, allowing users to continue with timeline adjustments or final editing in Studio as needed. This MCP uses the same infrastructure that powers ElevenLabs Agents, so if it was already installed for agent management, creative tools are available immediately without additional configuration. Workspace administrators can maintain security by selecting data residency regions and restricting accessible tools upon connection.