gen:music

What it does

Music as the deliverable: composed and rendered audio — a song, a jingle, a score, a loop — as the message designates. The kind is music; the instance rides in the prose.

The registry's own words: A piece of music as a deliverable: composed and rendered audio — a song, a jingle, a score, a loop — as the message designates.

Fire it — usage examples

“A twenty-second jingle for the moving company — bright, no lyrics. gen:music”

→ the jingle is composed, rendered, and delivered as audio.

“Background loop for the waiting room, calm, piano. gen:mu”

→ a loop is delivered — lyrics alone, or a playlist, would not be the music.

Said aloud: “Lingo, generate music — the jingle.”

→ the piece is delivered as an audio artifact.

Spoken. Inside a marked span opened by the wake word “Lingo”, the spoken form is “generate music”. Dictated directives fire deliberately, never by accident.

What the agent actually does

The agent composes and renders the piece the message designates — style, length, instrumentation, lyrics where asked — and delivers it as audio. A host that cannot render music says so; lyrics, a playlist, or a description are different artifacts, offered only as disclosed substitutes, never as the piece.

The baseline procedure, its edge cases, and this directive's full guide live in the implementation guide: implementation/IMPLEMENTATION.md#cmd-gen-music ↗.

When the host can't

No generation capability for music on this host: disclose it plainly, never fake a piece, and never silently substitute lyrics, a playlist, or another kind of audio for it. A description of the music is not the music.

Conformance — “done when”

The composed piece is delivered as rendered audio, or the missing capability is disclosed.

Persistence class: content-write. Execution report in the reply: required. A user can test any of this by hand — fire the directive, then check the result against the store, the schedule, or the reply itself.