heartmula

Generate original music tracks from lyrics and tags using open-source models.

Updated Jul 6, 2026

Search Tags:#ai #audio #generation #music #lyrics #songs

Ready to run

npx skills add https://github.com/ghufronbagaskara/agent-im --skill heartmula-ghufronbagaskara

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/ghufronbagaskara/agent-im/tree/main/hermes-home/skills/media/heartmula
Command: npx skills add https://github.com/ghufronbagaskara/agent-im --skill heartmula-ghufronbagaskara

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of generating high-quality, original music locally without relying on expensive or restrictive proprietary cloud services.

Core Features & Use Cases

Lyrics-to-Song Generation: Transforms structured lyrics and descriptive tags into full-length audio tracks.
High-Fidelity Codec: Utilizes the HeartCodec model for professional-grade audio reconstruction.
Use Case: A content creator can generate custom background music for a video project by providing specific mood tags and verse-chorus structured lyrics directly to the local model.

Quick Start

Use the heartmula skill to generate a song from the lyrics file located at assets/lyrics.txt using the provided tags file.

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 locally?▼

You generate music from lyrics by providing structured text and descriptive tags to the model, which synthesizes high-fidelity audio tracks locally without proprietary cloud services.

Do I need a CUDA-enabled GPU to generate audio tracks?▼

Yes, you need a CUDA-enabled GPU environment with PyTorch and specific model checkpoints to perform high-fidelity local audio synthesis.

Can I use PyTorch and Transformers for AI-assisted songwriting?▼

Yes, you can use PyTorch and Transformers for AI-assisted songwriting by conditioning open-source foundation models on input lyrics and tags to generate original music tracks.

What is the best way to create custom background music for video projects?▼

The best way to create custom background music is providing specific mood tags and verse-chorus structured lyrics directly to the local model for professional-grade audio reconstruction.

How does the HeartCodec model work for audio generation?▼

The HeartCodec model provides professional-grade audio reconstruction, transforming structured lyrics and descriptive tags into full-length, high-fidelity audio tracks.

Are there limitations when using open-source models for music synthesis?▼

Open-source music synthesis limitations include requiring a CUDA-enabled GPU environment and specific model checkpoints, meaning local generation cannot run on standard CPU-only hardware.