> For the complete documentation index, see [llms.txt](https://diff-svc.gitbook.io/the-beginners-guide-to-diff-svc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://diff-svc.gitbook.io/the-beginners-guide-to-diff-svc/project-overview.md).

# Project Overview

* Diff-SVC is an open-source Singing Voice Conversion project using the Diffusion model.

GitHub repository: <https://github.com/prophesier/diff-svc>\
Author: [prophesier](https://github.com/prophesier)

{% hint style="info" %}
If you are posting content created with this project on social media, it's recommended to include the GitHub repository link in the description, or **at least label it** as AI/SVC/Diff-SVC somewhere.
{% endhint %}

{% hint style="danger" %}
It is your responsibility to follow any rules and local laws that may apply when creating and sharing models.
{% endhint %}

## Pipeline Overview

<figure><img src="/files/57D0kpoqN4xK5Di6Byv7" alt=""><figcaption><p>Pipeline Overview (Simplified)</p></figcaption></figure>

In this guide, we will go through the 4 stages of the Diff-SVC pipeline: **Dataset Preparation**, **Preprocessing**, **Training**, and **Inference**.

### 24kHz or 44.1kHz

Some commands and configs will be slightly different depending on the vocoder you choose. The 44.1kHz vocoder will output audio at a higher sampling rate than the 24kHz one, which usually leads to higher audio quality. So it's recommended to use 44.1kHz to train new models.

## SVC & SVS

Singing Voice Conversion aims to **convert** one singer's voice to another's while Singing Voice Synthesis aims to **generate** singing voices from music scores and lyrics.

> Example:
>
> * SVS:&#x20;
>   * VOCALOID&#x20;
>   * UTAU
>   * Synthesizer V
>   * *DiffSinger*
>   * ...
> * SVC&#x20;
>   * Vocaloid 6 (VocaloChanger feature)
>   * ***Diff-SVC***
>   * ...

Diff-SVC is an SVC project, hence it takes vocal audio instead of midi and lyric as input. Check the partner project [DiffSinger](https://github.com/openvpi/DiffSinger) if you are looking for an open-source SVS project.

## Relationship between Diff-SVC and Diffsinger

> [DiffSinger](https://github.com/MoonInTheRiver/DiffSinger) (paper & code) -> [DiffSinger](https://github.com/openvpi/DiffSinger) (OpenVPI's Fork) -> [Diff-SVC](https://github.com/prophesier/diff-svc) (by\@prophesier)

Diff-SVC is based on DiffSinger, DiffSinger (openvpi maintenance version), and [soft-vc](https://github.com/bshall/soft-vc).

{% hint style="warning" %}
This project has NO connection with the [paper](https://arxiv.org/abs/2105.13871) of the same name DiffSVC, please do not confuse them!
{% endhint %}