741,000+ skills indexed

perasyudhaCOMMUNITY

Explore all skills by this author →

Verified:Website 𝕏@Nyxora_AI GitHub

heartmula

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

5|2|Updated May 26, 2026

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

One-click install

npx skills add https://github.com/perasyudha/Nyxora --skill heartmula-perasyudha

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: heartmula
Source: https://github.com/perasyudha/Nyxora/tree/main/packages/core/playbooks/media/heartmula
Command: npx skills add https://github.com/perasyudha/Nyxora --skill heartmula-perasyudha

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating original music with vocals typically requires expensive proprietary services like Suno or professional production skills. This Skill lets you generate complete songs locally from lyrics and style tags using the open-source HeartMuLa model family, with full offline control and no per-generation costs. ## Core Features & Use Cases - Lyrics-to-Song Generation: Produces full MP3 songs (48kHz stereo) conditioned on bracketed lyrics and comma-separated style tags using 3B/7B models. - Local & Offline Operation: Runs entirely on your own GPU with downloadable checkpoints, supporting lazy loading to fit in 8GB VRAM. - Multilingual Support: Includes HeartCodec for high-fidelity audio reconstruction and HeartTranscriptor for lyrics transcription. - 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 4-minute MP3 in about 4 minutes on a single GPU. ## Quick Start Ask the agent to install HeartMuLa from the heartlib repository, download the model checkpoints, and generate a song from your lyrics file and style tags.

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 your lyrics file, tags file, and output path. A 4-minute song takes roughly 4 minutes on a CUDA GPU.

What is a good open-source alternative to Suno?▼

HeartMuLa is an Apache-2.0 open-source music foundation model family that generates full songs from lyrics and tags, comparable to Suno. 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 loading enabled, making 8GB the minimum. 16GB or more is recommended for comfortable use, and multi-GPU setups can split the language model and codec across devices.

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

Yes, CPU mode works via --mula_device cpu --codec_device cpu, but generation is extremely slow, potentially 30-60+ minutes per song with 12GB+ RAM required. Without a GPU, a cloud GPU service or the online demo is recommended.

Why does HeartMuLa fail after installing with pip?▼

The pinned dependencies conflict with newer packages, so datasets and transformers must be upgraded manually. Two source patches are also required: a RoPE cache reinitialization fix and ignore_mismatched_sizes for HeartCodec loading.

What audio format and quality does HeartMuLa output?▼

HeartMuLa outputs MP3 files at 48kHz stereo, 128kbps. Keep HeartCodec in float32 precision rather than bfloat16, since bf16 degrades the reconstructed audio quality.

Related Skills

Explore More Design & Creative Skills→

heartmula

Generate MP3 music from lyrics and tags using HeartMuLa models.

KaiserWhoLearns

FFmpeg Audio Processing

Extract, normalize, and mix audio from video files using FFmpeg commands.

whisper

Transcribes audio files to text using OpenAI Whisper models via the Pixazo API gateway.

ai-music-generation

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