ワンクリックで
music-generation
AI music generation via Replicate — 5 models for background tracks, lyrics, and sound design
メニュー
AI music generation via Replicate — 5 models for background tracks, lyrics, and sound design
Create and maintain ASCII visual dashboards for project tracking with parallel lane progress bars
Store and manage voice samples for TTS cloning — portable, version-controlled audio references
Clear documentation through visual excellence
Practitioner methodology for longitudinal case study research, evidence-based documentation, and publication-ready academic writing in AI-assisted development.
First impressions matter. Set projects up for success.
Cloud TTS via Replicate — 15 models, voice cloning, emotion control, and multi-language support
| name | music-generation |
| description | AI music generation via Replicate — 5 models for background tracks, lyrics, and sound design |
| tier | extended |
| applyTo | **/*music*,**/*soundtrack*,**/*audio*,**/*score* |
| $schema | ../SKILL-SCHEMA.json |
Domain: AI Music Generation
Version: 1.0.0
Last Updated: 2026-04-15
Author: Alex (Master Alex)
Source: Patterns from AlexVideos CLI toolkit
Related: text-to-speech (voice), video-generation (video)
Generate AI music and soundtracks via Replicate. 5 models covering lyrics-based songs, instrumental tracks, and professional sound design.
| Key | Model | Replicate ID | Cost | Features |
|---|---|---|---|---|
music15 | MiniMax Music 1.5 | minimax/music-1.5 | $0.03/file | Lyrics with [verse], [chorus] tags |
music01 | MiniMax Music 01 | minimax/music-01 | $0.035/file | Reference audio input |
stableaudio | Stable Audio 2.5 | stability-ai/stable-audio-2.5 | $0.20/file | Diffusion-based, 1–190s |
elevenmusic | ElevenLabs Music | elevenlabs/music | $8.30/1k sec | Professional, vocals toggle |
lyria2 | Google Lyria 2 | google/lyria-2 | $2/1k sec | Negative prompt support |
| Model | prompt | lyrics | duration | reference | negative | vocals |
|---|---|---|---|---|---|---|
music15 | ✅ | ✅ | — | — | — | ✅ auto |
music01 | ✅ | — | — | ✅ | — | — |
stableaudio | ✅ | — | 1–190s | — | ✅ | — |
elevenmusic | ✅ | — | variable | — | — | ✅ toggle |
lyria2 | ✅ | — | variable | — | ✅ | — |
| Need | Model | Why |
|---|---|---|
| Song with lyrics | music15 | Structured lyrics with verse/chorus |
| Match existing style | music01 | Reference audio input |
| Budget instrumental | stableaudio | Cheapest per-file |
| Professional production | elevenmusic | Highest quality, vocal toggle |
| Exclude unwanted elements | lyria2, stableaudio | Negative prompt support |
Use structured tags for song sections:
[intro]
(Soft piano melody)
[verse]
Walking through the city lights at night
Every shadow tells a different story
Searching for a meaning in the dark
Finding hope in unexpected places
[chorus]
We rise above the noise
Breaking through the silence
Every heart beating as one
Together we are stronger
[bridge]
When the world falls apart around us
We'll find our way back home
[outro]
(Fade out with gentle strings)
const output = await replicate.run("minimax/music-1.5", {
input: {
prompt: "Uplifting pop rock song about finding hope",
lyrics: `
[verse]
Walking through the rain...
[chorus]
We are the dreamers...
`,
},
});
const output = await replicate.run("stability-ai/stable-audio-2.5", {
input: {
prompt: "Epic cinematic orchestral score, heroic theme, brass and strings",
duration: 60, // seconds
negative_prompt: "vocals, singing, speech, drums",
},
});
const output = await replicate.run("minimax/music-01", {
input: {
prompt: "Upbeat electronic dance track",
reference_audio: referenceAudioDataURI, // Sample to match style
},
});
const output = await replicate.run("elevenlabs/music", {
input: {
prompt: "Energetic pop song with catchy hook",
include_vocals: true, // or false for instrumental
},
});
| Element | Good Example | Avoid |
|---|---|---|
| Genre | "lo-fi hip hop", "orchestral cinematic" | "good music" |
| Mood | "melancholic", "uplifting", "tense" | "nice" |
| Instruments | "acoustic guitar, soft piano, strings" | "instruments" |
| Tempo | "slow ballad 60 BPM", "upbeat 120 BPM" | — |
| Structure | "builds to crescendo", "ambient loops" | — |
| Model | Cost | Quality | Notes |
|---|---|---|---|
| stableaudio | ~$0.20 | Good | Budget, diffusion-based |
| music15 | ~$0.03 | Good | Best for lyrics |
| music01 | ~$0.035 | Good | Style matching |
| lyria2 | ~$0.12 | High | Negative prompts |
| elevenmusic | ~$0.50 | Premium | Professional quality |
avmerge| Use Case | Recommended Flow |
|---|---|
| YouTube video music | stableaudio → descriptive prompt → 60–120s |
| Song demo | music15 → structured lyrics → review |
| Brand audio logo | stableaudio → 5–10s → specific style prompt |
| Podcast intro | stableaudio → 15–30s → upbeat, no vocals |
| Film score | lyria2/elevenmusic → cinematic prompt → long form |
import { writeFileSync } from "fs";
// Music typically returns MP3 or WAV
const response = await fetch(output);
const buffer = await response.arrayBuffer();
writeFileSync("output.mp3", Buffer.from(buffer));