> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody.md).

# Convai Embody

Find the setup guides, API reference, and design notes for Convai Embody, which renders a talking 3D body for a Convai character on the web.

Convai Embody renders a Convai character as a 3D body in a web page and drives its lip sync, gaze, breathing, and blinking while the character talks. It is built on the [Convai Web SDK](https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-web-sdk.md) and uses one connection for both, so a page needs a credential and a character ID and nothing else. The current release is <code class="expression">space.vars.embody\_version</code>.

<figure><img src="https://413558230-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEtUJA212Zc1S9ACc8T4l%2Fuploads%2Fgit-blob-4c03e6bbbd731630c93e714844291966f7c15b69%2Fsample-avatars-busts.jpg?alt=media" alt="Four Convai sample avatars rendered by Convai Embody in a dark studio: two women in patterned head wraps and two men, one in a cap and tunic and one in scrubs with a stethoscope, lit by one key light with soft shadows"><figcaption><p>Sample avatars rendered by Convai Embody under a single key light: skin, hair, eyes and cloth take the scene's lighting.</p></figcaption></figure>

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Get started with Convai Embody</strong><br>Create a new React app, render a character, and talk to it through the chat widget.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/get-started.md">Get started with Convai Embody</a></td></tr><tr><td><strong>Add a 3D character to a React app</strong><br>Install the package, render a character, and confirm that it speaks with lip sync.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/add-a-3d-character-to-a-react-app.md">Add a 3D character to a React app</a></td></tr><tr><td><strong>Add a 3D character to a three.js scene</strong><br>Use the framework-free API in an existing three.js renderer and render loop.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/add-a-3d-character-to-a-three-js-scene.md">Add a 3D character to a three.js scene</a></td></tr><tr><td><strong>Add a chat widget to a character</strong><br>Let users type and talk to the character through the same connection.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/add-a-chat-widget-to-a-character.md">Add a chat widget to a character</a></td></tr><tr><td><strong>Add your own animations to a character</strong><br>Load your own clips, crossfade between them, and play a talking clip while the character speaks.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/add-your-own-animations.md">Add your own animations to a character</a></td></tr><tr><td><strong>Use your own 3D model</strong><br>Render a character with a MetaHuman GLB you host, with Full and Lite files.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/use-your-own-3d-model.md">Use your own 3D model</a></td></tr><tr><td><strong>React API reference</strong><br>Props, defaults, and return values for the React components and hooks.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/react-api-reference.md">React API reference</a></td></tr><tr><td><strong>createCharacter reference</strong><br>Options and the returned character handle for the framework-free API.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/createcharacter-reference.md">createCharacter reference</a></td></tr><tr><td><strong>How Convai Embody works</strong><br>How a character ID becomes a body, and why motion runs in a fixed order.</td><td><a href="https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody/how-convai-embody-works.md">How Convai Embody works</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/web-plugins/convai-embody.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
