> 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/vision.md). # 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.	How vision works
Vision quick start Add the Environment Webcam component to a character and confirm scene vision works in one Play In Editor session.	Vision quick start
Vision frame sources Configure the built-in Environment Webcam component, its render target, capture rate, and active source selection.	Vision frame sources
Custom vision components Create a C++ frame source when the built-in Environment Webcam component does not cover your image pipeline.	Custom vision components
Vision Blueprint reference Reference for Blueprint-accessible vision enums, component properties, events, and Chatbot integration nodes.	Vision Blueprint reference
Vision usage examples Apply common Blueprint patterns for auto-start capture, manual start and stop, FPS tuning, and source switching.	Vision usage examples
Troubleshoot vision Diagnose missing visual context, failed starts, blank render targets, invalid sources, and capture-rate problems.	Troubleshoot vision

### Next steps Start with [How vision works](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/vision/how-vision-works.md) to understand the capture pipeline. Then follow [Vision quick start](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/vision/vision-quick-start.md) before tuning capture settings in [Vision frame sources](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/vision/vision-frame-sources.md) or applying patterns in [Vision usage examples](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/vision/vision-usage-examples.md). --- # 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/convai-unreal-engine-plugin/features/vision.md?ask=&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.