Generate music from lyrics and tags using HeartMuLa models.
npx skills add https://github.com/x-TheFox/Corvus --skill heartmula-x-thefox
Please help me install this Agent Skill. Skill: heartmula Source: https://github.com/x-TheFox/Corvus/tree/main/skills/media/heartmula Command: npx skills add https://github.com/x-TheFox/Corvus --skill heartmula-x-thefox
HeartMuLa provides open-source tools to generate music conditioned on lyrics and tags, enabling offline, customizable music creation without relying on proprietary models. It encompasses a family of components (HeartMuLa, HeartCodec, HeartTranscriptor, HeartCLAP) to deliver end-to-end music generation, audio encoding, transcription, and alignment.
Use cases include generating songs from lyrics and tags locally, building custom music generation apps, and offline workflows for creative production.
Run a local generation workflow using the provided assets and models to synthesize music from a lyrics file and a tags file.
High-intent search queries and answers about installing and using this skill.
Open-source music generation from lyrics and tags allows offline creation using local hardware. This Skill provides models and assets to synthesize audio directly from text inputs without relying on cloud APIs or proprietary services.
Yes, local music generation workflows support multilingual lyric inputs. The integrated transcription component processes various languages, enabling you to condition the music generation models on diverse linguistic text.
A music codec encodes audio into a compressed representation and decodes it back. The included 12.5Hz codec reconstructs high-fidelity audio from the generated outputs, ensuring the final synthesized music retains rich acoustic quality.
Open-source music generation supports multi-hardware environments for offline workflows. The provided installation steps and models allow you to configure and run the generation process on various local hardware setups.
Audio-text alignment is achieved using a dedicated alignment model during the music synthesis workflow. This ensures the generated audio accurately matches the conditioning tags and lyrics you provided as input.
softweekSynthesize local text-to-speech audio with sherpa-onnx models.
ZardLi1115Generate music and sound effects from text prompts using Meta AudioCraft models.
juliuss1907Generate music from lyrics and tags using open-source models.
ChatCut-IncGenerate original background music audio from descriptive text prompts.
