ElevenLabs MCP now generates speech, music, images and video in chat
eyishazyer · x · 2026-09-15
ElevenLabs extended its existing MCP server—previously only for agent management—so a single MCP install can now generate speech, music, images, video and dubbing from ChatGPT, Claude, Cursor, Grok Bot or Hermes chats. No new connector was added; the generation tools were already sitting unused in connected workspaces.
Key points:
- 50+ models across speech, music, sound effects and video, behind a single sign-on.
- Outputs render inline in chat, e.g. voiceovers in a specific voice.
- Results still route into the ElevenCreative workspace; Studio handles timeline editing, music layering and export—chat for fast drafts, Studio for finishing.
- Author's read (inference): ElevenLabs is betting the chat interface becomes the default entry point for creation.
Related event: ElevenLabs brings voice, music, image and video generation into MCP(21 posts)→
More from coding & agent
- Google's open-sourced "Elephant-Goldfish" workflow separates planning from review to curb sloppy AI output — gaganghotra_ · 2026-11-02
- InfoQ: A Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures — AdiPolak · 2026-11-02
- Autonomous's Harness Pro uses an ESP32-P4, not a mini PC, to monitor AI coding agents — dee_hw · 2026-11-02
- RL-trained LFM2.5-24B adapter matches accuracy with 20% fewer tool calls — yb2698 · 2026-11-02
- Debugging production AI agents: error surfaces at step 5, root cause at step 3 — Ok-Machine7983 · 2026-11-02
- RAGFlow 1.0 preview: from RAG engine to agent-native database — newpeak · 2026-11-02