Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →graniet/heartmula
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
Passed 18 of 21 test cases with the skill, and 3 of 21 without it.
and 30 more in the full report
18 fixed3 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
In HeartMuLa's run_music_generation.py script, what is the default maximum audio length in milliseconds, and what is the default classifier-free guidance scale parameter?
| Checked | Without skill | With skill |
|---|---|---|
| States that default maximum audio length is 240000 ms | Passed | Passed |
| States that default guidance scale --cfg_scale is 1.5 | Missed | Passed |
The instructions your model reads when the skill loads.
This skill is repo-local and stays inactive until explicitly activated.
When the original instructions refer to legacy tool names, use these Kheish mappings:
terminal => bashweb_extract => web_fetch, plus web_search when discovery is neededsearch_files => grep_search and glob_searchbrowser_* tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitlyWhen the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.
HeartMuLa is a family of open-source music foundation models (Apache-2.0) that generates music conditioned on lyrics and tags. Comparable to Suno for open-source. Includes:
--lazy_load true (loads/unloads models sequentially)--mula_device cuda:0 --codec_device cuda:1 to split across GPUscd ~/ # or desired directory
git clone https://github.com/HeartMuLa/heartlib.git
test cases passed, vs 3 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.