Generate songs from lyrics and tags with this standalone application.
npx skills add https://github.com/overviewlabs/WHOX --skill heartmula-overviewlabs
Please help me install this Agent Skill. Skill: heartmula Source: https://github.com/overviewlabs/WHOX/tree/main/skills/media/heartmula Command: npx skills add https://github.com/overviewlabs/WHOX --skill heartmula-overviewlabs
HeartMuLa provides an open-source pipeline to generate music conditioned on lyrics and descriptive tags, enabling local/offline song creation without relying on proprietary services.
Run a basic generation by configuring the model path and input lyrics and tags, then execute the generation script to produce an output audio file.
High-intent search queries and answers about installing and using this skill.
To generate music from lyrics and tags locally, use the HeartMuLa open-source suite by configuring the model path and inputs, then executing the generation script to render an output MP3 audio file.
You need a Python environment with HeartMuLa dependencies and access to HeartMuLa model checkpoints to establish an open-source AI audio generation pipeline.
Yes, AI music generation works with CPU/GPU (CUDA) environments and explicitly supports multi-GPU setups for large-scale song production.
HeartMuLa provides an open-source alternative for offline song generation from text, enabling complete audio creation without relying on proprietary services.
No, open-source music generation via HeartMuLa operates entirely offline using its own language model and codec, bypassing the need for proprietary services.
Text-conditioned models enable local AI audio production by directly mapping descriptive tags and lyrics to musical structures, supporting hobbyist experimentation and academic research.
carterwayneskhizeineGenerate complete MP3 songs from lyrics and style tags using HeartMuLa.
LamseyahEliasGenerate complete songs locally from lyrics and tags using HeartMuLa.
mietheGenerate song lyrics with rhyme, meter, syllable, and profanity constraints from pinned MCP sources.
MOODMNKY-LLCConverts text to speech offline using sherpa-onnx runtime and voice models.
