Vision

Give Convai characters scene vision in Unreal Engine so they can respond to what is visible in the level during conversation.

Vision lets a Convai character see the Unreal level during conversation. You add a scene-capture component to the character, point it at the area the character should watch, and Convai uses those frames alongside speech.

How vision works Understand how scene frames are captured, discovered, and sent to Convai during a session.

Vision quick start Add the Environment Webcam component to a character and confirm scene vision works in one Play In Editor session.

Vision frame sources Configure the built-in Environment Webcam component, its render target, capture rate, and active source selection.

Custom vision components Create a C++ frame source when the built-in Environment Webcam component does not cover your image pipeline.

Vision Blueprint reference Reference for Blueprint-accessible vision enums, component properties, events, and Chatbot integration nodes.

Vision usage examples Apply common Blueprint patterns for auto-start capture, manual start and stop, FPS tuning, and source switching.

Troubleshoot vision Diagnose missing visual context, failed starts, blank render targets, invalid sources, and capture-rate problems.

Next steps

Start with How vision works to understand the capture pipeline. Then follow Vision quick start before tuning capture settings in Vision frame sources or applying patterns in Vision usage examples.