> 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/convai-unreal-engine-plugin/features.md).

# Features

Features are the plugin's AI-powered capability modules. Each feature connects to Convai for a specific purpose — executing in-scene behaviors, expressing emotions, remembering players across sessions, following authored narrative graphs, or perceiving the world through a camera. Every section includes a conceptual overview, a quick start, Blueprint property references, usage examples, and troubleshooting guidance.

Select a feature to get started:

<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>Character actions</strong><br>Let Convai return structured action sequences your Blueprint event handlers execute — move to objects, follow the player, or run any custom behavior.</td><td><a href="/pages/NjVHOB3MELicvSSurEPd">/pages/NjVHOB3MELicvSSurEPd</a></td></tr><tr><td><strong>Dynamic context</strong><br>Push live runtime state — health, inventory, zone, events — into the character's context window mid-session without restarting the connection.</td><td><a href="/pages/VtreGBSkV3v9EqIKSNQH">/pages/VtreGBSkV3v9EqIKSNQH</a></td></tr><tr><td><strong>Emotion</strong><br>Translate Convai emotion signals into per-emotion blendshape weights and scores on any skeletal character.</td><td><a href="/pages/dXQYIyvmX3Z6hN65zfqt">/pages/dXQYIyvmX3Z6hN65zfqt</a></td></tr><tr><td><strong>Long-term memory</strong><br>Give characters cross-session recall via Speaker IDs and session continuity — characters remember individual players, facts, and past interactions over time.</td><td><a href="/pages/DMTej4CYSOHRGmpxRVHi">/pages/DMTej4CYSOHRGmpxRVHi</a></td></tr><tr><td><strong>Narrative design</strong><br>Structure character behavior around an authored story graph — sections define objectives and tone, triggers advance the narrative, template keys inject live gameplay data.</td><td><a href="/pages/adQWw1CiOcNdZRsmpBeB">/pages/adQWw1CiOcNdZRsmpBeB</a></td></tr><tr><td><strong>Scene metadata</strong><br>Tag world actors with <code>UConvaiObjectComponent</code> so Convai characters know which objects exist in the scene and can reference them by name in conversation.</td><td><a href="/pages/vbGxc89Y9wflNJFl3EW4">/pages/vbGxc89Y9wflNJFl3EW4</a></td></tr><tr><td><strong>Vision</strong><br>Stream scene frames from a capture component to Convai so characters can perceive and discuss what the player sees in real time.</td><td><a href="/pages/5TGq7ASz4xWw1Dhn8qy3">/pages/5TGq7ASz4xWw1Dhn8qy3</a></td></tr><tr><td><strong>Gaze attention</strong><br>Use player line-of-sight to direct which scene object a character focuses on — sustained gaze promotes objects to active attention with configurable dwell timers.</td><td><a href="/pages/LWOprxC8MMYzTxzOV4pu">/pages/LWOprxC8MMYzTxzOV4pu</a></td></tr><tr><td><strong>Lip sync</strong><br>Drive mouth and face blendshapes in sync with Convai speech using <code>UConvaiFaceSyncComponent</code> — supports MetaHuman, ARKit, CC4, and viseme targets.</td><td><a href="/pages/MUqoUJUdEwZL84AyCxoU">/pages/MUqoUJUdEwZL84AyCxoU</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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
