> For the complete documentation index, see [llms.txt](https://docs.hyungpt.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hyungpt.app/fundamentals/advanced-customization/custom-voices-beta.md).

# Custom Voices (Beta)

Within a session, hyunGPT can send voice messages:

<figure><img src="/files/jQ5jplBuHbh8d3vvOMgy" alt=""><figcaption></figcaption></figure>

In order to enable this feature, you must set a custom voice via `/session set_voice` and upload an mp3 (audio) file of the voice you would like to replicate. After done so, hyunGPT will now reply with an audio message along with it's regular message to all messages.

### What are the restrictions?

Currently, hyunGPT's custom voice feature have a few restrictions:

1. We only support English language as of now

### What makes a good audio file?

In order to have good results with your custom voice, it is crucial to upload an audio file with the following:

1. A clear, crisp, audio file, without background noise
2. Only the voice that you would like to replicate, without other voices (e.g. a podcast clip would not be good, as there are usually more than one voice).
3. An MP3 audio file with a length greater than 30 seconds.

### Where can I find a good audio file?

Sometimes, it can be difficult to find a good audio file! Don't worry, we have your back.

If you want to clone your own voice:

1. Record yourself speaking for about a minute, it can be a story, article, or something else.
2. Make sure there is no background noise or other voices in the audio recording. Find a quiet place to record!

If you want to use someone else's voice:

1. If they are a public figure, always make sure that you have their permission!
2. If it's a public figure, you can most likely find clips of them talking on a social media site such as YouTube. Try to find a video of only them talking, with no other voices.
3. Once you have found a YouTube video, you can download the mp3 of it using a site like <https://cobalt.tools/> , make sure to download the audio, not the video.

And that's it! Note that the voice messages will not sound perfect, as we're still developing and improving this feature!


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.hyungpt.app/fundamentals/advanced-customization/custom-voices-beta.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.