heartmula

Generates songs from lyrics and tags using the open-source HeartMuLa model.

1|Updated Jun 9, 2026
One-click install
npx skills add https://github.com/aivos-xie/hermes-skills --skill heartmula-aivos-xie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/aivos-xie/hermes-skills/tree/main/media/heartmula
Command: npx skills add https://github.com/aivos-xie/hermes-skills --skill heartmula-aivos-xie

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires heartlib, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill allows users to generate full songs from given lyrics and tags, offering a localized, open-source alternative to Suno for music creation.

Core Features & Use Cases

  • Song Generation: Automatically generate complete songs based on user-provided lyrics and tags.
  • Multilingual Support: Works with lyrics in multiple languages.
  • Open-Source Models: Utilizes open-source models, HeartMuLa and HeartCodec, for high-fidelity music generation.
  • Use Case: If you have a set of lyrics and want to create a song with a specific mood or genre, this Skill can generate music that complements your lyrics.

Quick Start

Generate a song from the lyrics 'I want to be with you forever' with the tags 'love, acoustic, soft' by running the command generate_song 'I want to be with you forever' ['love', 'acoustic', 'soft'].

Frequently Asked Questions about heartmula

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a song from lyrics and tags offline?

To generate a song from lyrics and tags offline, you use the HeartMuLa model by providing your text lyrics and mood descriptors. This allows localized AI-driven music creation without relying on cloud-based platforms like Suno.

What is an open-source Suno alternative for AI music creation?

An open-source Suno alternative for AI music creation is the HeartMuLa model. It generates full songs directly from user-provided lyrics and tags, enabling high-fidelity music generation in a local environment.

Do I need HeartMuLa and HeartCodec to generate music from text?

Yes, you need both HeartMuLa and HeartCodec to generate music from text descriptions. These open-source models work together to process your lyrics and tags to produce high-fidelity audio output.

How do I create a song with specific genres using tags?

You create a song with specific genres by passing your lyrics and an array of tags into the generation command. For example, use `generate_song 'lyrics' ['love', 'acoustic', 'soft']` to set the desired mood.

Does open-source music generation support multilingual lyrics?

Yes, open-source music generation with HeartMuLa supports multilingual lyrics. You can provide lyrics in multiple languages, and the model will generate music that complements your text.