Skip to content
@ALIZARINENGINE

ALIZARIN ENGINE

Official ALIZARIN Engine. Open-source (LGPLv3) framework for fully synthetic, ethical voices. (TTS | DiffSinger | UTAU).

Welcome to the ALIZARIN ENGINE Organization

License: LGPL v3 Discord


🚀 Our Mission

Our mission is to create a high-level, open-source, and experimental framework for stylized non-human ethical vocal synthesis.

The Alizarin Engine is a project designed to generate multiple types of voice products—including real-time TTS, AI singing, and concatenative singing—all from a single, 100% synthetic voice source. We are focused on empowering creators with powerful tools to author entirely new synthetic voices, giving them deep control to produce heavily stylized and unique timbres, such as those inspired by retro speech synthesis.

📖 Get Started

Whether you're a developer, a voice creator, or just curious, here's where you'll want to go to learn more:

💖 Character Rights & Special Requests

This section covers the usage rights for our official characters (like the Alizarin Engine Voice) and their associated IP. While our engine is open-source, our official characters are our brand, and their use is more strictly controlled.

Non-commercial fan art and fan fiction are encouraged! For all other uses, please see the "Special Requests" process (detailed in our USAGE_GUIDE.md) if you wish to:

  • Request permission to use an official character's name for song credits (e.g., "Song featuring ALIZARIN").
  • Inquire about a commercial license for using the character's name or artwork (e.g., on merchandise or album covers).
  • Propose an official collaboration or addition to one of our main, official voicebanks.
  • Request a one time exception for a use case restricted by our standard character rights (like R-18 content).

💬 Join the Community

Our official Discord is the central hub for our community. It's the best place to get support, find collaborators for your voice, and share what you've created.

⚖️ Licensing & Ethical Use

This project is built on a foundation of ethical, open-source development. All use of this project and its outputs are subject to the following agreements.

🛠️ How to Contribute

We are actively developing the Alizarin Engine and welcome collaborators of all kinds!

For Developers:

Check our roadmap and open issues to see where you can help.

  • See our Roadmap (Projects): View the high-level plan, see what's in progress, and find out what's coming next.
  • Check Open Issues: Find bug reports and feature needs. This is the best place to start contributing code.

We Need Linguists & Data Curators!

This project's success depends on more than just code. We are actively seeking help in the following areas:

  • Native Language Support: Do you have expertise in phonetics for a non-English language? We need help building the phoneme maps, accent rules, and synthesis data for native engine support.
  • RVC Data Oversight: We need community members to help oversee and manage the RVC hybrid workflow, helping connect VAs with creators and ensuring ethical guidelines are followed.

If you have this expertise, please introduce yourself on our Discord!

Popular repositories Loading

  1. DiffSingerAlizarin DiffSingerAlizarin Public

    Forked from MoonInTheRiver/DiffSinger

    DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS) Custom fork to be updated to work within the Alizarin Engine.

    Python

  2. AlizarinEngine AlizarinEngine Public

    The ALIZARIN Engine is a high-level experimental voice framework for generating multiple voice synthesis products (real-time TTS, AI singing, and concatenative singing) from a single, 100% syntheti…

  3. .github .github Public

Repositories

Showing 3 of 3 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…