> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tavus.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Understand Tavus Faces, learn how to create your own using a video or an image, or explore ready-to-use stock Faces.

## What is a Face?

A **Face** is how a **[PAL](/sections/conversational-video-interface/pal/overview)** 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](/sections/faces/which-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](/sections/faces/phoenix-45-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.

**Input**

* **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](/sections/faces/voices-for-image-based-faces).

<Note>
  Creating a custom face is **only available** on the Starter, Growth, and Enterprise plans.
</Note>

## Stock Faces

Alternatively, Tavus offers 100+ ready-to-use [stock Faces](/sections/faces/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](/sections/faces/stock-faces#pro).

## Key Features

<CardGroup cols={3}>
  <Card title="Realistic Face Cloning" icon="face-smile">
    Custom faces capture a person's look, expressions, and speaking style.
  </Card>

  <Card title="Emotional Control" icon="arrows-repeat">
    Faces express emotions through lifelike facial expressions while speaking and listening.
  </Card>

  <Card title="Full Motion Control" icon="head-side">
    Smooth transitions between speaking and listening with fully generated, natural head and (on Phoenix-4.5) torso motion.
  </Card>
</CardGroup>

## Platform Policies

By using PAL Maker and the Tavus APIs, you agree to comply with Tavus' [Terms of Service](https://www.tavus.io/terms-of-service) and [Acceptable Use Policy](https://www.tavus.io/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](https://maker.tavus.io/dev/faces/create).
* For API flows, use [Video to Face](/sections/faces/video-to-face-quickstart) or [Image to Face](/sections/faces/image-to-face-quickstart). For which model to pick, recording rules, and best practices, see [Choose a Model and Training Path](/sections/faces/which-training-path).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.