heartmula

Generate music tracks from lyrics and tag prompts using HeartMuLa.

1|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/cryptopafi/nexusos-skills --skill heartmula-cryptopafi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/cryptopafi/nexusos-skills/tree/main/media/heartmula
Command: npx skills add https://github.com/cryptopafi/nexusos-skills --skill heartmula-cryptopafi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables local, open-source generation of full music tracks from structured lyrics and tag prompts, providing an alternative to closed-source models for users who need offline or self-hosted audio generation.

Core Features & Use Cases

  • Model Suite: Includes HeartMuLa for lyric-conditioned music generation, HeartCodec for high-fidelity audio reconstruction, HeartTranscriptor for lyrics transcription, and HeartCLAP for audio-text alignment.
  • Flexible Deployment: Supports lazy loading to reduce VRAM, multi-GPU splitting for performance, and CPU fallback for environments without NVIDIA GPUs.
  • Practical Use Cases: Compose multilingual songs from prompts and lyrics, generate demos for artists, and batch-produce short songs for prototypes or creative workflows.
  • Operational Notes: Requires Python 3.10, manual dependency upgrades and two source patches described in the documentation, and several gigabytes of pretrained checkpoints to be downloaded prior to generation.

Quick Start

Generate a 3-minute upbeat song from these lyrics and tags and save the output as output.mp3 using HeartMuLa with lazy_load enabled.

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 from lyrics and tags locally?

To generate full songs locally, you input structured lyrics and tag prompts into the music generation workflow, which outputs high-fidelity audio tracks. The process supports multilingual lyrics and batch production for creative prototypes.

Can I run open-source music generation without an NVIDIA GPU?

Yes, open-source music generation can run without an NVIDIA GPU using a CPU fallback environment. The system also supports lazy model loading to reduce VRAM usage and multi-GPU splitting for enhanced performance when GPUs are available.

What Python environment is required for local audio generation?

Local audio generation requires a Python 3.10 environment. You must also manually upgrade dependencies, apply two source patches described in the documentation, and download several gigabytes of pretrained checkpoints before generating tracks.

Does this audio generation workflow support multilingual lyrics?

Yes, the audio generation workflow supports multilingual lyrics. You can compose full songs from prompts containing lyrics in various languages, making it suitable for diverse music generation and artist demo creation.

Why does my local music generation model fail to load?

Local music generation models may fail to load if VRAM is exceeded, but enabling lazy loading reduces memory usage. Additionally, ensure you have downloaded all required pretrained checkpoints and applied the documented source patches.