> 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/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment.md).

# 具身化

查找为 Convai 角色提供眼神接触、手势、姿势和表情的模块，并了解应先添加哪一个。

一个只会说话的 Convai 角色可能会显得呆板：它的目光没有焦点，姿势一成不变，面部也不会对说话内容做出反应。具身化是 Convai 对一组组件的统称，这些组件能为角色补上这些行为——它看向哪里、如何移动、如何保持姿势，以及说话时面部呈现出什么表情。每个模块都是可选的，而且可以独立工作，因此只需添加项目所需的模块，其余模块可以不添加。

***

### 五个具身化模块

| 模块   | 组件                                 | 对角色的作用                                       |
| ---- | ---------------------------------- | -------------------------------------------- |
| 对话流程 | `ConvaiConversationFlowController` | 跟踪角色处于空闲、聆听、思考还是说话状态。其他四个模块会读取此状态，而不是各自跟踪状态。 |
| 注视   | `ConvaiGazeController`             | 决定角色看向哪里——与玩家进行眼神交流、扫视，以及转移注意力。              |
| 身体动画 | `ConvaiBodyAnimationController`    | 从动画集播放待机、说话动作、行走和手势动画。                       |
| 肢体语言 | `ConvaiBodyLanguageController`     | 添加环境姿势、呼吸和细微的应激动作，让角色在有意执行动作的间隙保持生动。         |
| 情绪   | `ConvaiEmotionController`          | 驱动面部表情和情绪，其中一部分依据随 Convai 响应一同传来的信号。         |

这五个模块都继承自同一个基类，并注册到每个角色共用的对象中，因此它们能够协同工作，而不会相互覆盖。有关这个共享模型，请参阅 [角色具身化](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/character-embodiment.md) ；有关 Conversation Flow 跟踪的状态，请参阅 [对话状态](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/dialogue-state.md) 。

***

### 从哪里开始

先添加 **Gaze** 。它是一个独立组件，无需制作动画集或配置文件；它带来的效果——角色与玩家进行眼神交流——也是在 Play 模式下最容易辨认的具身化行为。Conversation Flow 是基础模块，但通常无需手动添加：其他模块首次需要读取对话状态时，Convai 会自动添加它。

{% content-ref url="/pages/73e995564a424dd193e693891d64a815b3e79450" %}
[具身化快速入门](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/quick-start.md)
{% endcontent-ref %}

***

### 各个模块

<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>Gaze</strong><br>眼神交流、扫视物体和其他角色，以及让身体转向角色正在关注的对象。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/gaze.md">视线</a></td></tr><tr><td><strong>Body animation</strong><br>待机、说话动作、行走、手势和指向动作；这些动作从动画集播放，无需制作 Animator Controller。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/body-animation.md">身体动画</a></td></tr><tr><td><strong>Body language</strong><br>持续的环境动作——姿势、呼吸、重心转移、小动作和反应动作。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/body-language.md">肢体语言</a></td></tr><tr><td><strong>Conversation flow</strong><br>对话状态时钟，其他模块会读取它来安排自身动作的时机。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/conversation-flow.md">对话流程</a></td></tr><tr><td><strong>Emotion</strong><br>面部表情和持续时间较长的情绪，由随 Convai 响应传来的信号驱动，也可以通过自己的代码设置。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/emotion.md">情绪</a></td></tr></tbody></table>

***

### 探索具身化

<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>具身化的工作原理</strong><br>运行时概览：Convai 会为每个角色配置哪些内容，以及各模块的运行顺序。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/how-embodiment-works.md">具身化如何运作</a></td></tr><tr><td><strong>具身化快速入门</strong><br>为现有角色添加一个模块，并在 Play 模式下查看效果。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/quick-start.md">具身化快速入门</a></td></tr><tr><td><strong>角色骨架设置</strong><br>了解 Convai 如何检测骨骼和混合形状，以及何时需要覆盖映射。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/character-rig-setup.md">角色骨架设置</a></td></tr><tr><td><strong>具身化预设</strong><br>将所有模块的设置打包到一个资源中，并在运行时切换该资源。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/embodiment-presets.md">具身化预设</a></td></tr><tr><td><strong>面部组合</strong><br>了解 Emotion 和 LipSync 如何共享嘴部、眉部及其他面部区域。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/facial-composition.md">面部组合</a></td></tr><tr><td><strong>具身化编辑器窗口</strong><br>用于检查角色具身化状态的 Setup、Presets 和 Live 选项卡。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/embodiment-editor.md">具身化编辑器窗口</a></td></tr><tr><td><strong>具身化脚本参考</strong><br>各模块共用的公开具身化 API。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/scripting-reference.md">具身化脚本参考</a></td></tr><tr><td><strong>排查具身化问题</strong><br>诊断 Convai 无法检测的骨架、缺失的骨骼，以及未执行更新的模块。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment/troubleshooting.md">排查具身化问题</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/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/embodiment.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.
