heartmula

Generate songs from lyrics and tags using HeartMuLa models.

Updated May 25, 2026
One-click install
npx skills add https://github.com/zaiyemeiyou404/Hermes --skill heartmula-zaiyemeiyou404
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/zaiyemeiyou404/Hermes/tree/main/backup/skills/media/heartmula
Command: npx skills add https://github.com/zaiyemeiyou404/Hermes --skill heartmula-zaiyemeiyou404

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides the ability to create music/songs based on text descriptions, using the HeartMuLa models, which generate music from lyrics and tags.

Core Features & Use Cases

  • Music Generation: Produces full songs from provided lyrics and tags.
  • Multilingual Support: Supports multiple languages for lyrics input.
  • Open-Source Alternative: Offers an open-source alternative to Suno for music generation.

Quick Start

Generate a song with the lyrics "I want to dance with you, under the moonlight" and tags "upbeat, pop, piano".

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 text tags?

To generate music from lyrics, you input your text descriptions alongside descriptive tags into the system. The neural network architecture processes these inputs to produce a full song track.

Can I use multilingual lyrics for AI audio generation?

Yes, you can use multilingual lyrics for AI audio generation. The system supports multiple languages for lyrics input, allowing you to create songs from text descriptions in various languages.

Does this open-source AI music generation work with PyTorch and Hugging Face?

Yes, this open-source AI music generation works with PyTorch and Hugging Face. It is built using dependencies like torch, transformers, and huggingface-hub to process lyrics and generate audio.

What is the best open-source alternative to Suno for lyric-based music generation?

An open-source alternative to Suno for lyric-based music generation utilizes neural network architectures to create songs. It produces full audio tracks directly from provided text lyrics and genre tags.

How do I create a complete song from a text description?

You create a complete song from a text description by providing lyrics and style tags. For example, inputting lyrics and upbeat pop tags generates a matching full audio track.

What are the limitations of generating audio from text descriptions?

Generating audio from text descriptions relies on neural network architectures and requires specific dependencies like torch and transformers. Users must provide both lyrics and tags to achieve the desired musical composition output.