Question 1

What are Avatars?

Accepted Answer

Avatars are persistent visual identities that you pair with any ElevenLabs voice to generate talking-head videos with synchronized lip movement. An Avatar can be a person, character, or animal. Once created, it lives in your workspace and can be reused across as many videos as you need.

Question 2

How do I create an Avatar?

Accepted Answer

Go to Image & Video or Studio, select the Avatar tab, and click New Avatar. Upload multiple reference images of the same person or character from different angles. Name the Avatar, add an optional description, and click Create. Multiple reference images produce the best results. Single-image results may be inconsistent.

Question 3

What are Styles?

Accepted Answer

Styles are variations of an existing Avatar. Different camera angles, outfits, backgrounds, or lighting conditions. You can generate new Styles from an existing Avatar or create them from scratch using additional reference images. This lets you keep the same identity across different visual contexts without rebuilding.

Question 4

Can I use my own voice with an Avatar?

Accepted Answer

Yes. You can select any voice from your library, including cloned voices, and pair it with any Avatar. Text to Speech is integrated directly into the Avatar prompt island, so the voice and the lip-synced video are produced together in one step.

Question 5

Which lip-syncing models are used?

Accepted Answer

We integrate multiple leading lip-syncing models. The platform selects the best model based on your input format and quality requirements. You do not need to choose a model manually.

Question 6

What plans include Avatars?

Accepted Answer

Avatars are available on all paid plans. Credit costs follow the existing Image & Video pricing structure and vary by model and resolution. Credits are shared across all ElevenCreative tools.

Question 7

Can I use Avatars in Flows?

Accepted Answer

Yes. A new Avatar node is available in Flows. You can build automated pipelines that generate avatar videos at scale, swapping scripts, voices, and Styles across runs. This is useful for producing dozens of ad variants or localized content in a single execution.

Question 8

Is there an Avatar API?

Accepted Answer

Not at initial launch. API access is planned for a future release.

Question 9

How is this different from using lip-sync models directly in Image & Video?

Accepted Answer

Previously, generating a lip-synced video meant opening Image & Video, selecting Video, filtering the model picker by lip-sync, and choosing a model. Avatars simplifies this into a single entry point with integrated Text to Speech, persistent identities, and a curated library. It reduces the steps from five to one.

Question 10

Can I use Avatars for animals or non-human characters?

Accepted Answer

Yes. Avatars support humans, characters, and animals. Upload reference images from different angles and the system generates the Avatar identity the same way it does for human subjects.

AI avatar generator

The best voices, now with a face

Create studio-grade talking videos from a script, a voice, and an avatar. Generated together, in one place.

How it works

Write your script

Pick a voice and avatar

Generate

Find the perfect Avatar

Create a persistent avatar from your own photos

Upload reference images

Generate styles

Keep consistent

Scale with Flows

Bring your content to life with the best-in-class models

Voice Cloning

Voice Design

Speech

Avatars

Headspace scales global meditation with ElevenProductions

Ramp accelerates creative production with ElevenLabs

Clay scales content production and agility with ElevenCreative

Frequently asked questions