heartmula

Generate songs from lyrics and tags using HeartMuLa music foundation models.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/ashiqcodeleaf/long-Run-Agents --skill heartmula-ashiqcodeleaf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/ashiqcodeleaf/long-Run-Agents/tree/main/skills/media/heartmula
Command: npx skills add https://github.com/ashiqcodeleaf/long-Run-Agents --skill heartmula-ashiqcodeleaf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torchtune, datasets, transformers, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows users to generate songs directly from lyrics and tags, providing an open-source alternative to Suno-like music generation.

Core Features & Use Cases

  • Music Generation: Generate full songs from provided lyrics and tags.
  • Lyrics & Tags: Supports input of lyrics with structured tags for specific song characteristics.
  • Use Case: A user with a set of lyrics and desired song attributes can use HeartMuLa to create a custom song.

Quick Start

Generate a song from the lyrics "I want to rock in the jungle" with the tag "rock, energetic".

Frequently Asked Questions about heartmula

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

FAQPage Schema
How do I generate music from lyrics and tags using AI?

AI music generation from lyrics requires providing structured text inputs like verses and style descriptors, which the model transforms into a complete custom song track.

Can I create a song with multilingual lyrics and custom style tags?

Yes, the music generation model supports multilingual lyrics input alongside structured descriptive tags to define specific song characteristics and styles.

Does this AI music generation model require PyTorch and Transformers?

Yes, AI music generation with this model requires PyTorch, torchtune, datasets, and transformers dependencies to execute the underlying foundation models.

What is the best open-source alternative to Suno for song creation?

Using open-source music foundation models provides a Suno-like alternative for song creation, generating full audio tracks directly from input text lyrics and style tags.

How do I structure tags for specific song characteristics when creating music?

Structure tags for song creation by providing descriptive genre and mood keywords alongside lyrics, guiding the model to generate music matching those specific characteristics.