skills.rest
joeseesun
joeseesunCOMMUNITY
Explore all skills by this author →
𝕏@vista8GitHub

music

Generate, remix, extend, and analyze AI music via the ListenHub Mureka CLI.

335|37|Updated Jul 18, 2026
Search Tags:#music generation#remix#soundtrack#ai music#stem separation#mureka#lyrics recognition
One-click install
npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill music-joeseesun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: music
Source: https://github.com/joeseesun/qiaomu-cut-skill/tree/main/vendor/marswaveai-skills/music
Command: npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill music-joeseesun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating original music, remixes, instrumentals, or soundtracks normally requires composition skills and studio tools; this Skill turns text prompts, lyrics, or reference media into finished AI-generated songs and also analyzes existing audio. ## Core Features & Use Cases - Music Generation: Create original songs from prompts and/or lyrics, generate pure instrumentals, score music to an image or video, extend songs, and isolate single instrument or vocal tracks using Mureka models. - Remixing: Re-create an existing song from an audio file, URL, or provider song ID with new lyrics and style direction. - Audio Analysis: Recognize lyrics with line-level timestamps, describe genres and instruments, and split songs into separated stems. - Use Case: Ask for a city pop remix of a demo MP3 with new lyrics; the Skill validates the file, confirms parameters, submits the async generation task, and downloads the finished track to your working directory. ## Quick Start Ask the assistant to generate a song about a summer beach with the music skill, then confirm the suggested style and title when prompted.

Frequently Asked Questions about music

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI music from a text prompt?▼

Use the generate capability with a prompt and optional lyrics, style, title, and model selection. The Skill submits an asynchronous task via the listenhub music CLI and downloads the finished MP3 to your current directory when generation completes.

How to remix an existing song with new lyrics using AI?▼

Provide one input source (an audio file, audio URL, or provider song ID) plus new lyrics and a prompt describing the direction. The remix command re-creates the song with Mureka models, and both lyrics and prompt are required parameters.

What audio file formats and sizes are supported for AI music generation?▼

Most commands accept mp3 and m4a files up to 10 MB, while the track command also accepts wav. Soundtrack generation accepts jpg, jpeg, png, webp images and mp4, mov, avi, mkv, webm videos, all capped at 10 MB.

Can I split a song into separate stems like vocals and drums?▼

Yes, the stem command splits a song into separated stems and returns ZIP download URLs. It runs synchronously with a choice of audio-separation-1 or audio-separation-2 models, and the ZIP is downloaded promptly in download output mode.

How long does AI music generation take?▼

Generation commands such as generate, remix, instrumental, and soundtrack are asynchronous and can take up to about 10 minutes. The CLI polls the task internally, and you can check status anytime with the list or get task commands.

When should I not use AI music generation?▼

Do not use it for text-to-speech reading, podcast discussions, explainer videos with narration, or transcribing spoken audio to text. Those tasks belong to dedicated speech, podcast, explainer, or ASR capabilities instead.

Related Skills

Explore More Design & Creative Skills→
Lineage-and-LoreLineage-and-Lore

acestep-simplemv

Render MP4 music videos from audio and LRC/JSON lyrics with Remotion.

Official
Intermediate
claude-office-skillsclaude-office-skills
368

Podcast Automation

Automate podcast production, editing, publishing, and distribution workflows.

Official
Advanced
Lineage-and-LoreLineage-and-Lore

acestep-thumbnail

Generate song cover and thumbnail images via the Gemini API.

Official
Intermediate
digitalsambadigitalsamba
1.9k

elevenlabs

Generate AI voiceovers, sound effects, and music via ElevenLabs APIs.

Official
Intermediate