754,000+ skills indexed

superfhpCOMMUNITY

Explore all skills by this author →

Verified:GitHub

heartmula

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

Updated May 13, 2026

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

One-click install

npx skills add https://github.com/superfhp/lumi-agent-body --skill heartmula-superfhp

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/superfhp/lumi-agent-body/tree/main/skills/media/heartmula
Command: npx skills add https://github.com/superfhp/lumi-agent-body --skill heartmula-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Producing original music typically requires composition skills, studio time, or paid services like Suno. This Skill lets you generate complete songs locally from plain-text lyrics and style tags using the open-source HeartMuLa model family, with no per-song fees and full offline control. ## Core Features & Use Cases - Lyrics-to-Song Generation: Generate full songs (up to 4 minutes, 48kHz stereo MP3) from bracketed lyrics and comma-separated style tags using 3B or 7B models. - Complete Audio Stack: Includes HeartCodec for high-fidelity audio reconstruction, HeartTranscriptor for lyrics transcription, and HeartCLAP for audio-text alignment. - VRAM-Conscious Operation: Lazy loading mode runs the 3B model in ~6.2GB VRAM, with multi-GPU splitting options for larger setups. - Use Case: A content creator needs a custom background song with specific lyrics for a video. They write lyrics with [Verse]/[Chorus] structure, specify tags like "piano,happy,wedding", and generate a ready-to-use MP3 in about 4 minutes on a single GPU. ## Quick Start Ask the AI to install HeartMuLa from the heartlib repository and generate a song from your lyrics file and style tags, saving the result as an MP3.

Frequently Asked Questions about heartmula

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

FAQPage Schema

How do I generate a song from lyrics with AI locally?▼

Install the heartlib package, download the HeartMuLa and HeartCodec checkpoints from Hugging Face, then run run_music_generation.py with a lyrics file using [Verse]/[Chorus] tags and a comma-separated tags file. Output is a 48kHz stereo MP3.

What open-source alternative to Suno exists for music generation?▼

HeartMuLa is an Apache-2.0 open-source music model family comparable to Suno, generating full songs from lyrics and tags. It includes a 3B/7B music language model, the HeartCodec audio codec, and multilingual support.

How much VRAM does HeartMuLa need to run?▼

The 3B model runs in about 6.2GB VRAM with lazy_load enabled, which loads and unloads models sequentially. 16GB or more is recommended for comfortable use, and multi-GPU splitting is supported via separate device flags.

Can HeartMuLa run on CPU or macOS?▼

CPU mode works via --mula_device cpu but is extremely slow, taking 30-60+ minutes per song versus about 4 minutes on GPU. Triton is unavailable on macOS, so GPU acceleration requires Linux with an NVIDIA GPU.

Why does HeartMuLa fail after installing with pip?▼

The pinned dependencies conflict with newer packages, requiring upgrades of datasets and transformers. Two source patches are also needed: RoPE cache reinitialization for transformers 5.x and ignore_mismatched_sizes for HeartCodec loading.

What audio quality and length does HeartMuLa produce?▼

Output is MP3 at 48kHz stereo, 128kbps, with a default maximum length of 240 seconds. Generation runs at roughly real-time, so a 4-minute song takes about 4 minutes on GPU.

Related Skills

Explore More Design & Creative Skills→

heartmula

Generate MP3 music from lyrics and tags using HeartMuLa models.

ai-music-generation

Generate music and songs from prompts using Diffrythm and Tencent Song Generation.

heartmula

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

ai-music-generation

Generates music and songs with AudioCraft and HeartMuLa, and analyzes audio via spectrograms.