Overview
Overview of Duix’s Avatar offerings- Stock Avatars and Personal Avatars, all powered by the AI model. Get tips on how to create the perfect avatar, and how to get a high quality output.
An Avatar is a realistic video model of a human created using the AI Model. The AI model is a fully-synthetic 2D based model that generates realistic avatar videos from just a script, complete with natural face (lip, cheek, nose, chin) movements and expressions synchronized with your script and generated voice. Developed by our team
Avatars are created using just 30 seconds of training data, and are designed to learn how someone speaks and sounds, how they look, and how they move their face while speaking. Using an Avatar you can generate hyper-realistic videos that look and sound just like you
It’s important to provide a high-quality input video in order to get great outputs from an Avatar. Your Avatar will attempt to mimic your gestures and movements, as well as your accent, even if you generate a video in a different language.
Here’s an example of an output from one of our Stock Avatars:
Personal Avatars
High-quality clone of voice and face of person
Train once, and re-use endlessly without having to record again
Personal Avatars allow you to train a new Avatar of a human using the AI model, from just 30 seconds of training data. Personal Avatars take between 4-6 hours to train. You can only train Avatars using training data that has a verbal consent statement. Personal Avatars go through Voice and Face ID checks to ensure consent is present.