# Create AI-music with 'aiphoria'
Right now, there are two main ways to generate music: first - in a new chat from scratch, second - in the pre-made community chats.\
\
\&#xNAN;*▶️* [**Short video about creation and publishing process at aiphoria:**](https://youtu.be/GPmKvmhuqz8)
{% embed url="" %}
## How to create AI-music in the new chat:
### Step 1: Sing up
Go to the platform and sign up: [**https://beta.aiphoria.world**](https://beta.aiphoria.world/)
### Step 3: Select a preferred AI model
Click on the 'AI model picker', where you can select different AI models at any time
### Step 4: Select an audio AI model
Select one of the available audio models. For example, let's pick 'MusicGen'
### Step 5: Adjust model settings
Set the preferred duration of your audio generation. A common value is 20-30 seconds.
### Step 6: Type what you want to generate
Type at the bottom of the screen in the input box what you want to hear from the model
### Step 7: Wait a while for the result of your generation
🌠 Congratulations! You've generated AI-audio.
### Step 8: Now you can share it with your friends or post it on your public profile page
### Join our beta today:
---
# 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://aiphoria.gitbook.io/welcome/use-cases/create-ai-music-with-aiphoria.md?ask=
```
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.