What is a Face?
A Face is how a PAL looks. Train one from a photo or a video, or pick a stock face. Most faces are realistic humans. Other human styles, such as cartoon, anime, or Pixar-style, also work. Animals, mascots, and other non-human figures do not. With Tavus, you can create a face that looks like you - or use a stock face for instant prototyping. Faces capture natural expressions, tone, and presence so interactions feel human and engaging.Custom Faces
You create a custom face by picking a Phoenix model, then sending either a training video or a training image. See Choose a Model and Training Path for which to pick. Models- Phoenix-4.5 – A zero-shot preview is usable early (about a minute from a photo; a few minutes from video), then tunes in the background. The preview carries a visible watermark; the later tuned version does not. How to poll: Phoenix-4.5 Preview and Status.
- Phoenix-4 – Ready when the full training job finishes. Use this for full body, or when you specifically need the Phoenix-4 look and image rules.
- Video – Captures movement and creates a voice from the footage audio.
- Photo – Faster to set up. Attach a voice separately. See Voices for Image-Based Faces.
Creating a custom face is only available on the Starter, Growth, and Enterprise plans.
Stock Faces
Alternatively, Tavus offers 100+ ready-to-use stock Faces - great for quick prototyping, demos, or teams without access to custom training footage or images.- Pro faces – A hand-picked, top-performing set of stock faces. See Pro Faces.
Key Features
Realistic Face Cloning
Custom faces capture a person’s look, expressions, and speaking style.
Emotional Control
Faces express emotions through lifelike facial expressions while speaking and listening.
Full Motion Control
Smooth transitions between speaking and listening with fully generated, natural head and (on Phoenix-4.5) torso motion.
Platform Policies
By using PAL Maker and the Tavus APIs, you agree to comply with Tavus’ Terms of Service and Acceptable Use Policy. You are responsible for ensuring you have the necessary rights and permissions to upload and use any training data, including videos, images, voices, and likenesses.Getting Started
You can create a face using either the PAL Maker or the API, depending on your workflow.- For a guided face creation flow with upload checks and inline validation, use the PAL Maker.
- For API flows, use Video to Face or Image to Face. For which model to pick, recording rules, and best practices, see Choose a Model and Training Path.

