ElevenLabs Connector Chains Image, Video, and Lipsync

ElevenLabs teased a workflow that lets users generate an image, edit it, turn it into video, and sync it to speech, all within one connector.

ElevenLabs has previewed a new feature that folds several previously separate AI media steps into a single pipeline. According to a post from the company, a user can generate an image, make edits to it, animate that image into a video, and then apply lipsync, all without leaving one connector. The announcement, shared on X, frames the image and video tools as working "alongside" other existing capabilities, suggesting this connector sits within a broader toolkit rather than standing alone. Details beyond that framing were not specified in the post. Bundling generation, editing, animation, and lipsync into one connector points to a push toward end-to-end content creation, where creators wouldn't need to shuffle files between separate image generators, video animators, and voice-sync tools. For a company best known for voice and speech AI, adding a visual pipeline that ends in synced dialogue suggests an effort to let users go from a still image to a talking, animated clip in one continuous process. No pricing, availability timeline, or technical specifics were included in the source post, so it remains unclear when or how widely this connector will roll out. AIVIDEO.NEWS will follow up as ElevenLabs shares more about the feature.