eachlabs-music — Claude Code skill: music and setup
The eachlabs-music skill connects coding agents to EachLabs Mureka models for songs, lyrics, speech, podcasts, and audio processing. Use it when a project needs generated or analyzed sound.
no license 1 installs ★ 48 updated 2026-10-07
npx skills add eachlabs/skills --skill eachlabs-music -a claude-codeWhat eachlabs-music does
eachlabs-music connects to the EachLabs Predictions API and exposes Mureka operations for making vocal songs, instrumental tracks, lyrics, speech, and multi-speaker podcasts. It can also continue an existing song, identify or describe audio, split a track into stems, and upload files for later requests.
The workflow checks a model slug first, submits a prediction with the matching schema, polls the prediction until it finishes, and reads the returned output. Authentication uses the EACHLABS_API_KEY environment variable; requests will fail authentication without that key. Song continuation has an extra step: upload the source audio first, then send its returned ID to the continuation operation.
Model-specific parameters are documented in references/MODELS.md. The skill can be installed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.
What it helps with
- generate a song from a genre and mood brief
- compose an instrumental backing track
- write or extend song lyrics
- produce a podcast with several speakers
- split an audio file into stems
Example prompts for the agent
- Create an indie pop song about a summer road trip with a catchy chorus.
- Make a relaxed instrumental with jazzy piano chords and vinyl texture.
- Upload my track, then continue it with an energetic guitar bridge.
How to install eachlabs-music
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-music -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-music/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-music/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-music -a codex2Manually: put the files in place
.agents/skills/eachlabs-music/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-music -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-music/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills skills/eachlabs-music2Manually: put the files in place
.github/skills/eachlabs-music/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-music -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-musicManually: put the files in place
.devin/skills/eachlabs-music/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-music -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about eachlabs-music
How do I install eachlabs-music in Claude Code?
Run npx skills add eachlabs/skills --skill eachlabs-music -a claude-code, then check ~/.claude/skills/eachlabs-music/SKILL.md.
What does eachlabs-music do?
It uses EachLabs Mureka models to create songs, instrumentals, lyrics, speech, and podcasts. It also handles song continuation, audio recognition and description, stem separation, and file uploads.
What is required to use the EachLabs API?
Set an API key in EACHLABS_API_KEY. To extend an existing song, upload the audio first and pass the returned upload ID to the next request.