# Edit avatar narration

{% hint style="info" %} <mark style="color:blue;">**Only users on the Premium or higher plans can customize the avatar's narration.**</mark>
{% endhint %}

Each speaking test is divided into multiple scenes such as **Introduction**, **Question 1**, **Question 2**... **Question N** and **Conclusion**. For each scene in the test, the avatar speaks a message appropriate for that scene. Using the edit avatar interface, test creators can customize what the avatar speaks during each scene. While most scenes are singular, a few scenes can also have sub-scenes. Test creators have the option to customize the narration for sub-scenes also.

A comprehensive list of scene and sub-scenes is available in the expandable box below for reference:

<details>

<summary>List of scenes for an avatar instance</summary>

Review the purpose of each scene before editing the avatar's narration, and follow the steps outlined in this document to make the changes.

1. **Scene**: Start\
   Purpose: Avatar will introduce the session, sets expectations, and gives an overview of what will happen.
2. **Scene**: Mic Check
   1. Sub-scene: Mic Check Introduction\
      Purpose: Avatar will start the mic check, prompting the user to test their microphone.
   2. Sub-scene: Mic Fail-1\
      Purpose: First failure message if the microphone isn’t detected or working properly.
   3. Sub-scene: Mic Fail-2\
      Purpose: Second failure message if the issue persists, with further instructions to resolve it.
   4. Sub-scene: Mic Fail-3\
      Purpose: Third failure message, possibly with more troubleshooting tips or alternative solutions.
   5. Sub-scene: Mic Success\
      Purpose: Confirmation that the microphone has been successfully detected and is working.
3. **Scene**: Test Introduction\
   Purpose: Avatar will introduce the test, explains its purpose, and outlines the instructions for the user.
4. **Scene**: Question `Number`
   1. Sub-scene: Introduction\
      Purpose: Avatar will present the question or task.
   2. Sub-scene: Prepare Answer\
      Purpose: Avatar will prepare the user to answer the question (e.g., providing a moment of thinking time).
   3. Sub-scene: Record Answer\
      Purpose: User records their response (if applicable, this could involve voice or text input).
   4. Sub-scene: Process Answer\
      Purpose: Avatar will process the answer provided by the user.
   5. Sub-scene: Process Failure\
      Purpose: If there’s an error in processing the answer, the avatar shall inform the user and prompts them to retry.
   6. Sub-scene: Process Success\
      Purpose: Confirmation that the answer was successfully processed.
5. **Scene**: Process Results\
   Purpose: Avatar will start processing the overall results of the test.
6. **Scene**: Results Failure\
   Purpose: Avatar will notify the user of an issue with processing the results.
7. **Scene**: Partial Results\
   Purpose: Avatar will narrate and display partial results or feedback if the process was not complete.
8. **Scene**: Results Success\
   Purpose: Avatar will provide the final results or feedback, confirming the successful completion of the task or test.

</details>

To edit the avatar narration for a scene, Select the Scene from the left pane and then click on the text box highlighted in Red below:

<figure><img src="/files/9tKQPrs29wITIWT0D5jm" alt=""><figcaption></figcaption></figure>

Once the avatar narration is edited, you will notice that both the Playback button for scene video and the Preview button for the activity are disabled. Furthermore, a message suggesting that a new avatar video needs to be generated for this scene is displayed as below:

<figure><img src="/files/ujTRBZrFMyxxu03UVTaB" alt=""><figcaption></figcaption></figure>

Now press the **Next** button to go to the screen where the avatar changes can be submitted for generating a revised avatar video.


---

# 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/edit-avatar/edit-avatar-narration.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.