# Customize avatars

Avatars are a core part of the speaking test's user experience. The avatars serve as virtual test conductors and provide instructions at every step of the test to the candidate. During the test creation process, the authors are provided a range of avatars to select from and also authors can select the avatar's language as shown below:

<figure><img src="/files/9PrDStlcI1iXsQbsLt5W" alt=""><figcaption></figcaption></figure>

While the default avatars provided during test creation have a general purpose narration script that can be applied to any speaking test, Premium plan customers have the option to further customize the narration script.&#x20;

Customizing the narration script can be used for the following purposes:

1. **Recite question instructions -** The avatar can be made to speak the question to the user and provide any additional information that the test creator may deem helpful in understanding questions.
2. **Provide branding information -** The avatar can be made to recite the branding information of the school or company which is organizing the speaking test.

Customizing the avatar is a three step process:

1. [Edit avatar](/speechace-speaking-test/speechace-workspaces-create-manage-and-share-speaking-assessments/customize-avatars/edit-avatar.md) - This is the first step, wherein an avatar's look and feel, language and narration is edited.
2. [Generate avatar](/speechace-speaking-test/speechace-workspaces-create-manage-and-share-speaking-assessments/customize-avatars/generate-avatar.md) - In this step, the edits to the avatar are submitted to a background job for generating a new avatar video. The background job generally finishes in a few minutes.
3. [Apply avatar](/speechace-speaking-test/speechace-workspaces-create-manage-and-share-speaking-assessments/customize-avatars/apply-avatar.md) - In this step, the newly generated video is previewed and applied to the assessment.

In the following sections, we will review these in detail.


---

# Agent Instructions: 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:

```
GET https://speaking-test-docs.speechace.com/speechace-speaking-test/speechace-workspaces-create-manage-and-share-speaking-assessments/customize-avatars.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.