> 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-unity-sdk/features/conversation-targeting.md). # Conversation targeting Find guides for choosing a targeting mode, tuning it, and scripting which character the player is addressing in a Convai Unity SDK room. Conversation targeting is how the Convai Unity SDK decides which character a player is talking to when a room holds more than one. `ConvaiManager` re-evaluates the decision continuously and moves the conversation to the character the player is addressing, without a component to add or a field that must be filled in.


How conversation targeting works Understand view-direction scoring, why the target only moves willingly, and why targeting lives on the manager rather than a component.	How conversation targeting works
Choose a targeting mode Pick between Look At, Proximity, and Manual based on your camera and control scheme.	Choose a targeting mode
Tune conversation targeting Adjust range, look angle, switch margin, and switch delay to fit your scene.	Tune conversation targeting
Script the conversation target Move the conversation from code with `TalkTo`, and set which character a room opens on with `SetInitialCharacter`.	Script the conversation target
Write a custom targeting rule Replace the built-in modes entirely by implementing `IConversationTargetProvider`.	Write a custom targeting rule
Conversation targeting reference Look up every public member of `ConversationTargetingOptions` and its defaults.	Conversation targeting reference
Troubleshoot conversation targeting Fix a target that will not switch, one that flickers, or one that never moves at all.	Troubleshoot conversation targeting

### How targeting fits into a scene Targeting only has something to decide once a scene registers more than one `ConvaiCharacter` with `ConvaiManager` — a room with one character has nothing to choose between. The setting lives under **Convai Manager → Who The Player Talks To** in the Inspector, and that section appears only once a second character is present. See [How multi-character sessions work](/api-docs/plugins-and-integrations/convai-unity-sdk/features/multi-character-sessions/how-multi-character-sessions-work.md) for how a room assembles its roster before targeting has anything to act on. ### Next steps Start with [How conversation targeting works](/api-docs/plugins-and-integrations/convai-unity-sdk/features/conversation-targeting/how-conversation-targeting-works.md) to understand the model, then [Choose a targeting mode](/api-docs/plugins-and-integrations/convai-unity-sdk/features/conversation-targeting/choose-a-targeting-mode.md) to pick the mode that fits your camera and controls. {% content-ref url="/pages/jcZc2BTDwRiUEN5KsfZz" %} [Multi-character sessions](/api-docs/plugins-and-integrations/convai-unity-sdk/features/multi-character-sessions.md) {% endcontent-ref %} --- # 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-unity-sdk/features/conversation-targeting.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.