Introducing Avatars

Introducing Avatars - a dedicated entry point for talking-head video in ElevenCreative. Try ElevenLabs → https://elevenlabs.io/avatars?utm_source=youtube&utm_medium=organic&utm_campaign=launch&utm_content=introducing_avatars Generating a lip-synced talking video used to mean navigating through model filters, choosing from providers you may not recognize, and stitching audio from a separate tool. Avatars reduces that to a single step: write a script, select a voice, choose an avatar, generate. Text to Speech is built directly into the prompt island so that voice and face are produced together. There is no audio export, no file handoff between platforms. The integration matters because ElevenLabs owns the speech layer - the voice model and the lip-syncing model run in the same environment, producing tighter synchronization than tools that rely on external audio imports. Avatars are persistent identities. Upload reference photos or write a prompt to create one, generate style variations across angles, outfits, and settings, and reuse the same identity across every video. For creators building a personal brand, this means a consistent on-camera presence without filming. For marketers running campaigns, it means visual consistency across dozens of ad variants without per-project production. The use cases extend well beyond UGC ads. Course creators can produce talking-head educational content at the pace of writing a script. Product marketers can generate explainer videos for every feature and every language. Social creators can maintain a recognizable presence across platforms without being on camera for every post. For teams producing at volume, the new Avatar node in Flows connects avatar generation into automated pipelines. Build a flow that takes a product brief, generates a script, creates a voiceover, and produces an avatar-led video - then batch-execute it across products, languages, and hooks from a single pipeline. Available on all paid plans. Try Eleven