heartmula

Install and run HeartMuLa models to generate songs from lyrics and tags.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11 --skill heartmula-cloudliness
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11/tree/main/skills/media/heartmula
Command: npx skills add https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11 --skill heartmula-cloudliness

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

HeartMuLa provides an open-source family of models that generate full songs conditioned on lyrics and descriptive tags, enabling offline, customizable music creation without vendor lock-in.

Core Features & Use Cases

  • HeartMuLa - Music language model (3B/7B) for generation from lyrics + tags
  • HeartCodec - 12.5Hz music codec for high-fidelity audio reconstruction
  • HeartTranscriptor - Whisper-based lyrics transcription
  • HeartCLAP - Audio-text alignment model

Quick Start

Install HeartMuLa, configure your hardware, and generate your first song from lyrics and tags.

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 offline?

To generate music from lyrics and tags offline, you can set up and run the open-source HeartMuLa model family on local hardware to create full songs without vendor lock-in.

What hardware do I need to run an open-source music generation model?

Running an open-source music generation model requires specific local hardware prerequisites to operate components like the 3B or 7B music language model and the 12.5Hz music codec.

Can I transcribe lyrics for audio generation using Whisper?

Yes, you can transcribe lyrics for audio generation using Whisper-based transcription components to process audio and align it with text using an audio-text alignment model.

How do I install and patch components for local music generation?

To install and patch components for local music generation, follow documentation steps to download models and configure the generation, codec, and transcription modules on your machine.

What is the best way to reconstruct high-fidelity audio from generated music?

The best way to reconstruct high-fidelity audio from generated music is by using a 12.5Hz music codec designed for high-fidelity audio reconstruction during the generation process.