741,000+ skills indexed

AvaTar-ArTsCOMMUNITY

Explore all skills by this author →

Verified:GitHub

heartmula

Generates full songs from lyrics and style tags using open-source HeartMuLa models.

Updated Jul 10, 2026

Search Tags:#gpu #music generation #open-source #text-to-music #heartmula #lyrics to song #ai audio

One-click install

npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill heartmula-avatar-arts

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/AvaTar-ArTs/.Agent-skills/tree/main/skills/media/heartmula
Command: npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill heartmula-avatar-arts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up and running open-source AI music generation locally involves complex installation steps, dependency conflicts, GPU configuration, and model patching that this Skill walks through end to end. ## Core Features & Use Cases - Song Generation from Lyrics and Tags: Produces complete MP3 songs (48kHz stereo) from bracketed lyrics and comma-separated style tags using the HeartMuLa 3B/7B models. - Guided Installation and Patching: Covers cloning heartlib, creating a Python 3.10 venv, fixing dependency conflicts, and applying required source patches for transformers 5.x compatibility. - Hardware-Aware Configuration: Supports lazy loading for 8GB VRAM GPUs, multi-GPU splitting, and CPU fallback with realistic performance expectations. - Use Case: A musician wants an open-source Suno alternative to prototype a song locally; this Skill installs HeartMuLa, downloads checkpoints, and generates a 4-minute track from their lyrics file. ## Quick Start Ask the assistant to install HeartMuLa and generate a song from your lyrics.txt and tags.txt files using the 3B model with lazy loading enabled.

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 with HeartMuLa?▼

Clone the heartlib repository, create a Python 3.10 virtual environment, download the HeartMuLa and HeartCodec checkpoints, then run examples/run_music_generation.py with your lyrics file, tags file, and output path. Use --lazy_load true on GPUs with limited VRAM.

What GPU do I need for HeartMuLa music generation?▼

HeartMuLa requires a minimum of 8GB VRAM with lazy loading enabled, which peaks around 6.2GB for the 3B model. 16GB or more is recommended, and you can split models across two GPUs with --mula_device and --codec_device flags.

Can HeartMuLa run on CPU or without an NVIDIA GPU?▼

Yes, HeartMuLa runs on CPU with --mula_device cpu --codec_device cpu, but generation is extremely slow, potentially 30-60 minutes per song versus about 4 minutes on GPU. Without a GPU, consider a cloud GPU service or the online demo instead.

Why does HeartMuLa fail after installing with transformers 5.x?▼

The pinned dependencies conflict with newer packages, and RoPE caches are not rebuilt after meta-device loading in transformers 5.x. Apply the documented patches to modeling_heartmula.py and music_generation.py, and upgrade datasets and transformers.

What are the limitations of HeartMuLa song generation?▼

Tags may be ignored since lyrics tend to dominate conditioning, Triton acceleration is unavailable on macOS, and RTX 5080 incompatibility has been reported. HeartCodec should also stay in float32 because bfloat16 degrades audio quality.

Related Skills

Explore More Design & Creative Skills→

minimax-music-gen

Generate vocal songs, instrumentals, and covers via the MiniMax Music API using the mmx CLI.

audio-mix

Layer narrator, music, and timed sound effects into MP3 or WAV audio files.

music-lyrics

Extract timestamped lyrics from audio using faster-whisper.

heartmula

Generate music and songs from lyrics and tags using HeartMuLa models.