Introducing Avatars in ElevenCreative

Avatars is a new entry point in ElevenCreative for generating talking-head videos. It pairs ElevenLabs speech models with leading lip-syncing models in a single interface - so creators and marketers can go from script to finished video without switching platforms.

One interface for voice and face

Previously, generating a lip-synced video in ElevenCreative required navigating to Image & Video, selecting the Video tab, opening the model picker, filtering by Lipsync, and choosing a provider. Avatars replaces that with a single tab: select your avatar, write your script, pick a voice, and generate.

Text to Speech is built directly into the prompt island so that the voice and the lip-synced video are produced together. There is no separate audio export step and no file handoff between platforms. Because ElevenLabs owns the speech layer, the voice model and the lip-syncing model run in the same environment - producing tighter synchronization than workflows that rely on external audio imports.

Create and reuse persistent identities

An avatar is a persistent visual identity built from reference images or a text prompt. Upload photos of a person, character, or animal, and ElevenCreative generates a base identity you can reuse across any number of videos. Avatars can be human or non-human, and each comes with a pre-selected default voice that you can change at any time.

Generate styles to create variations - different camera angles, outfits, and backgrounds - while maintaining the same underlying identity. The avatars you create or favorite live in your Assets and can be referenced in any prompt box or dragged directly into a generation.

This is designed for creators and marketers who need visual consistency across campaigns and content. A course creator can produce an entire video series with the same on-screen instructor. A brand can maintain a consistent spokesperson across every market and language. A social creator can scale their personal presence without filming every post.

Use avatars with video models

Avatars integrate with the video generation models available in ElevenCreative. Source images act as a character sheet so that the model maintains the same identity across scenes within a video. This lets creators build longer-form content with consistent characters rather than generating isolated clips.

Scale with Flows

A new Avatar node in Flows connects avatar video 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.

The applications range from performance marketing teams generating dozens of ad variants from a single pipeline, to education companies producing course content across subjects and languages, to product teams creating localized explainer videos for every market they serve.

Browse the avatar library

ElevenCreative includes a curated library of avatars and styles ready to use. Filter by age, gender, or use case, or browse the full collection. Each avatar supports multiple styles for different visual contexts.

Start creating with Avatars

Avatars is available today on all paid plans in ElevenCreative: elevenlabs.io/app/image-video