heartmula

An open-source music-generation system that creates full songs from lyrics and descriptive tags. Its models support multiple languages and can run locally when suitable computer hardware is available.

In plain words
What is it for?
Use it to generate songs from lyrics, create music from text descriptions, or run an open-source alternative to services such as Suno.
Why use it?
It provides a way to make songs from text without relying on a hosted music service, though generation requires a compatible graphics processor.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nousresearch/hermes-agent/heartmula
Any agent
npx skills add NousResearch/hermes-agent --skill heartmula
Clone the repo
git clone --depth 1 https://github.com/NousResearch/hermes-agent

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.01777
Opus 5 $0.00009 $0.00889
Sonnet 5 $0.00003 $0.00355
Haiku 4.5 $0.00002 $0.00178

Measured yesterday against content hash faf24624f590, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

heartmula scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

optional-skills/creative/heartmula/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HeartMuLa - Open-Source Music Generation

Overview

HeartMuLa is a family of open-source music foundation models (Apache-2.0) that generates music conditioned on lyrics and tags, with multilingual support. Generates full songs from lyrics + tags. Comparable to Suno for open-source. Includes:

  • HeartMuLa - Music language model (3B/7B) for generation from lyrics + tags
  • HeartCodec - 12.5Hz music codec for high-fidelity audio reconstruction
  • HeartTranscriptor - Whisper-based lyrics transcription
  • HeartCLAP - Audio-text alignment model

When to Use

  • User wants to generate music/songs from text descriptions
  • User wants an open-source Suno alternative
  • User wants local/offline music generation
  • User asks about HeartMuLa, heartlib, or AI music generation

Hardware Requirements

  • Minimum: 8GB VRAM with --lazy_load true (loads/unloads models sequentially)
  • Recommended: 16GB+ VRAM for comfortable single-GPU usage
  • Multi-GPU: Use --mula_device cuda:0 --codec_device cuda:1 to split across GPUs
  • 3B model with lazy_load peaks at ~6.2GB VRAM

Installation Steps

1. Clone Repository

cd ~/  # or desired directory
git clone https://github.com/HeartMuLa/heartlib.git
cd heartlib

2. Create Virtual Environment (Python 3.10 required)

uv venv --python 3.10 .venv
. .venv/bin/activate
uv pip install -e .

3. Fix Dependency Compatibility Issues

IMPORTANT: As of Feb 2026, the pinned dependencies have conflicts with newer packages. Apply these fixes:

# Upgrade datasets (old version incompatible with current pyarrow)
uv pip install --upgrade datasets

# Upgrade transformers (needed for huggingface-hub 1.x compatibility)
uv pip install --upgrade transformers

4. Patch Source Code (Required for transformers 5.x)

Patch 1 - RoPE cache fix in src/heartlib/heartmula/modeling_heartmula.py:

In the setup_caches method of the HeartMuLa class, add RoPE reinitialization after the reset_caches try/except block and before the with device: block:

Read the full file on GitHub · 174 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 174 lines · 17 tokens per session scan A faf24624f590

Subscribe to this mod's changes

heartmula is a skill published in the GitHub repository NousResearch/hermes-agent (238,457 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,777 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

bootstrap-realtime-eval

Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…

openai/openai-cookbook · 76 tokens

create-design-system

Skill to use if user asks you to create a design system or UI kit.

asgeirtj/system_prompts_leaks · 19 tokens

9router-video

Generate videos via 9Router /v1/videos/generations using xAI Grok Imagine (grok-imagine-video). Async job flow - submit, poll requestid until done, download MP4. Use when the user wants to create, generate, or render a video, text-to-video (txt2vid), or image-to-video.

decolua/9router · 74 tokens

9router-image

Generate images via 9Router /v1/images/generations using OpenAI / Gemini Imagen / DALL-E / FLUX / MiniMax / SDWebUI / ComfyUI / Codex models. Use when the user wants to create, generate, draw, or render an image, picture, or text-to-image (txt2img).

decolua/9router · 74 tokens

9router-stt

Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.

decolua/9router · 63 tokens

9router-tts

Text-to-speech via 9Router /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud.

decolua/9router · 70 tokens