# Adding Custom Voice

Upload audio to create your own unique voice.

{% hint style="warning" %}
The custom voice feature is currently in `beta` version and is being provided to a limited number of users. If you have any questions about the custom voice feature, please [contact our sales team](https://www.aivatar.ai/en/contactus).
{% endhint %}

### 1. Accessing Custom Voice Menu

1. Enter the [<mark style="color:blue;">`Language and Voice Settings`</mark> menu.](/user-guide/usage/using-aivatar/configure-voice/language.md)
2. Click the <mark style="color:blue;">`Custom Voices`</mark> tab.
3. Click the <mark style="color:blue;">`Create Own Voice`</mark> button.

### 2. Setting Upload Voice Options

#### 2. 1. Setting a Name

You can specify a name for the custom voice you're adding.

* Names must consist of Korean, Roman alphabet, or numbers without spaces.
* Maximum 15 characters.
* Cannot duplicate names of other custom voices you've already created.

#### 2.2. Selecting Gender

Select the gender of the voice you're uploading.

{% hint style="warning" %}
If you select a gender different from the uploaded voice, the final added voice may sound unnatural.
{% endhint %}

#### 2.3. Selecting Noise Reduction Level

You can select the level of noise reduction based on the background noise in your uploaded audio.

* You can listen to sample files to hear the expected results of noise removal at <mark style="color:blue;">`Low`</mark>, <mark style="color:blue;">`Medium`</mark>, and <mark style="color:blue;">`High`</mark> levels.

{% hint style="info" %}
Please select <mark style="color:blue;">`High`</mark> if your upload has significant noise, <mark style="color:blue;">`Medium`</mark> for moderate noise, and <mark style="color:blue;">`Low`</mark> if there's minimal noise.
{% endhint %}

#### 2.4. Moving to the Voice Upload Step

After setting the name, gender, and noise reduction level, click the <mark style="color:blue;">`Next`</mark> button in the upper right to proceed to the voice upload step.

#### 2.5. Going Back

You can exit the custom voice addition process at any time by clicking the <mark style="color:blue;">`Go Back`</mark> button in the upper left.

### 3. Uploading Audio

#### 3.1. File Upload

Upload the audio file you want to create as a custom voice.

1. You can upload audio files using the following methods:
   1. Click the <mark style="color:blue;">`Upload File`</mark> button to select and upload a file from your local storage.
   2. Drag and drop a file from your local storage.
2. Uploaded files must meet the following requirements:
   * [x] File must have a `WAV` or `MP3` extension.
   * [x] Audio length must be between 10 to 30 seconds.
   * [x] Audio quality must be 16,000Hz or higher.

#### 3.2. Reviewing Precautions and Agreeing to Data Processing

You must review and agree to the following terms regarding your uploaded audio file.

> Your uploaded audio file will be used solely for generating custom voice samples and creating voices within the workspace. AIPARK CO.,LTD will not use this data for any other purpose. The uploaded audio file will be stored and used for the duration of custom voice service availability in the workspace.
>
> You acknowledge that you will not use content generated on the AiVATAR platform and all services with AiVATAR technology (including API) for illegal or harmful purposes. You are prohibited from using audio files that infringe on others' rights and acknowledge potential legal liability for unauthorized use of copyrighted audio. Additionally, you agree to comply with AIPARK CO.,LTD's terms of service, prohibited content and usage policies, and privacy policy.
>
> By clicking '<mark style="color:blue;">`Create`</mark>', you acknowledge and agree to all the above terms.

{% hint style="warning" %}
Please carefully review this information as it contains terms you must understand and agree to.
{% endhint %}

#### 3.3. Proceeding to Creation

Click the <mark style="color:blue;">`Create`</mark> button in the upper right to automatically start creating your custom voice.

{% hint style="info" %}
If your file doesn't meet the requirements in [#id-3.1.-file-upload](#id-3.1.-file-upload "mention"), you may need to upload a different audio file.
{% endhint %}

#### 3.4. Returning to the Previous Step

Click the <mark style="color:blue;">`Previous`</mark> button in the upper right to return to step [#id-2.-setting-upload-voice-options](#id-2.-setting-upload-voice-options "mention").

### 4. Creating and Applying Custom Voice

1. After meeting all requirements in step [#id-3.-uploading-audio](#id-3.-uploading-audio "mention"), the custom voice creation will begin.
   * Creating a custom voice may take several minutes. The process will continue even if you leave the current screen.
   * You cannot attempt to create a new custom voice while one is already being generated.
2. When custom voice creation is complete, voice cards will be added for 140 languages, with 1-3 cards per language.
   * Custom voice names will be formed by adding `_A`, `_B`, `_C` to the name set in step [#id-2.-1.-setting-a-name](#id-2.-1.-setting-a-name "mention").
3. To apply the custom voice, click on the custom voice card in your desired language, then click <mark style="color:blue;">`Apply`</mark> to apply the voice to your currently selected paragraph.

### 5. Additional Information

#### 5.1. Number of Uploaded Voices

You can upload a maximum of 1 voice for now. The current status is displayed to the right of the <mark style="color:blue;">`Create Own Voice`</mark> button at the top of the screen as <mark style="color:blue;">`Number of Voices | Maximum Upload Limit`</mark>.

#### 5.2. Viewing Voices by Upload

Click the <mark style="color:blue;">`See All`</mark> dropdown menu in the upper right to view a list of all custom voices you've created.

* Click <mark style="color:blue;">`See All`</mark> to display all custom voices.
* Click on a specific custom voice name to display only that voice.


---

# 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://aivatar.gitbook.io/user-guide/usage/using-aivatar/configure-voice/custom-voice.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.