ElevenLabs MCP adds voice, music, image, video generation — and a user got a buyer
heyshrutimishra · x · 2026-09-15
ElevenLabs launched an MCP integration that generates speech, transcripts, dubs, music, sound effects, images and video from your existing assistant. One user made an announcer voice for a fake trailer as a joke, sent it to three people, and one wanted to buy it — a joke turning into a real product.
More from Multimodal
- Muse video generation glitch: band members' legs keep disappearing — zats · 2026-09-15
- Genspark Design tested: one visual direction produces a full layered brand system — AiBreakfast · 2026-09-15
- Omni-Streaming Thinking: deferring claims until cross-modal verification — Enjun Du · 2026-09-15
- Phota Identity V2: train a persistent identity from 5 photos in 1 minute — stuffyokodraws · 2026-09-15
- How to remove the "AI sheen": making a generated character look real — DeviceCapital7041 · 2026-09-15
- GPT Image 2.5 consistency demo: 16-frame grid turned into GIF — gefei55 · 2026-09-15