skills.rest
xiaoquqi
xiaoquqiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

heartmula

Convert lyrics and tags into complete songs using an offline music generation workflow.

Updated May 1, 2026
Search Tags:#ai#offline#generation#music#multilingual#lyrics
One-click install
npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill heartmula-xiaoquqi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/xiaoquqi/hermes-agent-skills/tree/main/media/heartmula
Command: npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill heartmula-xiaoquqi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and scripts (resource) and references (resource) components.

What problem does it solve?

HeartMuLa reduces barriers to high-quality, offline music generation by providing an open-source, self-contained workflow that turns lyrics and tags into complete songs, without relying on cloud APIs.

Core Features & Use Cases

  • HeartMuLa: Music language model that generates songs from lyrics and tags with multilingual support.
  • HeartCodec: 12.5Hz codec for high-fidelity audio reconstruction.
  • Usage scenarios include local music production, research on AI music generation, and offline demos on single or multi-GPU setups.
  • Suitable for environments needing privacy, offline capability, and reproducible results.

Quick Start

Run the music generation workflow using the provided model checkpoints and assets to generate an MP3 locally.

Frequently Asked Questions about heartmula

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

FAQPage Schema
How do I generate full songs locally from lyrics without using cloud APIs?▼

Offline music generation converts lyrics and tags directly into complete songs without relying on cloud APIs. This workflow uses model checkpoints and assets to generate MP3 files locally, ensuring privacy and reproducible results.

Does offline AI music generation support multilingual lyrics?▼

Yes, offline AI music generation supports multilingual lyrics. The underlying music language model processes lyrics and tags in multiple languages to generate complete songs locally.

Can I run local music production workflows on multi-GPU setups?▼

Local music production workflows support both single and multi-GPU setups. This allows users to scale offline music generation, research, and demos according to available hardware.

What is the best way to achieve high-fidelity audio reconstruction for offline demos?▼

High-fidelity audio reconstruction is achieved using a 12.5Hz codec. This codec processes the model's output to ensure high-quality audio reconstruction for offline demos and local music production.

How does a music language model convert text tags into songs?▼

A music language model converts lyrics and tags into songs by processing text inputs through modular model components. It generates audio that is then reconstructed by a codec into a complete MP3 file.

Why choose open-source music generation for research and local production?▼

Open-source music generation provides a self-contained workflow for research and local production. It eliminates cloud API dependencies, ensuring privacy, offline capability, and reproducible results across multi-GPU setups.

Related Skills

Explore More Software Engineering Skills→
nomad3nomad3

sherpa-onnx-tts

Generates offline speech audio from input text to WAV using sherpa-onnx CLI tools.

Community
Intermediate
akselikorhonen-siiliakselikorhonen-siili

play-audio

Play audio files from the command line with volume control.

Community
Basic
projectedanxprojectedanx
1

audiocraft-audio-generation

Generate music and sound effects from text prompts using Meta's AudioCraft models.

Community
Advanced
photonics-dhlphotonics-dhl

heartmula

Set up HeartMuLa and generate songs locally from lyrics and tags.

Community
Advanced