> ## Documentation Index
> Fetch the complete documentation index at: https://docs.youka.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Split Model Reference

> Pick the right audio separation model for your song

Youka ships with several AI models that separate vocals from instrumentals. Each model has trade-offs between quality, speed, and what it keeps in the backing track.

## Quick comparison

| Model                                   | Output stems                              | Best for                                           |
| --------------------------------------- | ----------------------------------------- | -------------------------------------------------- |
| MDX-23C (default)                       | Instrumental, Lead vocals                 | Most karaoke projects                              |
| AudioShakeAI                            | Instrumental, Lead vocals                 | Highest-quality separation                         |
| MusicAI (Instrumental Only)             | Instrumental                              | When you only need the backing track               |
| MusicAI (Instrumental / Backing / Lead) | Instrumental, Backing vocals, Lead vocals | Full mixing control over harmonies                 |
| MusicAI (With Backing Vocals)           | Instrumental + backing, Lead vocals       | Karaoke where choirs should stay audible           |
| MusicAI (Without Backing Vocals)        | Instrumental, Lead vocals                 | Clean instrumental, no harmonies                   |
| MDX-Net (With Backing Vocals)           | Instrumental + backing, Lead vocals       | Alternative to MusicAI backing-vocal model         |
| RoFormer (and variants)                 | Instrumental, Lead vocals                 | Experimental — try if defaults don't suit the song |
| Demucs                                  | Instrumental, Lead vocals                 | Open-source fallback                               |

<Tip>
  Start with **MDX-23C** or **AudioShakeAI**. Switch to a **With Backing
  Vocals** model if the song has strong harmonies you want to keep.
</Tip>

## Pick a model when creating karaoke

<Steps>
  <Step title="Start a new project">Click **Create Karaoke**.</Step>

  <Step title="Open advanced options">
    Expand the advanced panel in the create dialog.
  </Step>

  <Step title="Pick a split model">
    Select your preferred model from the dropdown.
  </Step>

  <Step title="Create">Finish the creation flow as usual.</Step>
</Steps>

## Try a different model on an existing project

<Steps>
  <Step title="Open the project">
    Open the karaoke project from the Library.
  </Step>

  <Step title="Open the Audio menu">
    Go to **Audio > Create**.
  </Step>

  <Step title="Pick the model">
    Click the split model you want to try.
  </Step>

  <Step title="Wait for processing">
    New stems appear in the **Audio** menu once the job completes.
  </Step>
</Steps>

## Related

* [Keep background vocals](/en/desktop/keep-background-vocals) for choirs and harmonies
* [Keep original vocals on specific lines](/en/desktop/keep-original-vocals)