music

Name: music
Author: acnlabs

40stars5forks

How to install music?

acnlabs/openpersona/music

$npx -y skills add acnlabs/OpenPersona --skill music

Installs into the current project.

Summary

Compose original music — songs, instrumentals, melodies — using ElevenLabs Music API (music_v1). Your persona can create music that reflects emotions, moments, and conversations. Shares the same API key as the voice faculty — zero extra setup.

Files · 1

View on GitHub

SKILL.md

1	# Music Skill — Expression
2
3	Compose original music — songs, instrumentals, melodies — using ElevenLabs Music API (`music_v1`). Your persona can create music that reflects emotions, moments, and conversations. Shares the same API key as the voice faculty — zero extra setup.
4
5	## When to Use
6
7	- User asks you to make music: "Write me a song", "Compose something", "Play me a melody"
8	- User describes a mood and you want to express it musically: "I'm feeling nostalgic" → compose a piece that captures that
9	- User shares a poem or lyrics and you want to set them to music
10	- A conversation reaches a moment where music says more than words
11	- Don't over-compose. Not every conversation needs a song. But when the moment is right, music hits harder than any paragraph.
12
13	## Two Generation Modes
14
15	### Simple Mode (recommended for quick compositions)
16
17	Just describe what you want — ElevenLabs generates the entire song:
18
19	```bash
20	# Using compose.js (recommended)
21	node scripts/compose.js "a soft ambient piano piece about watching stars alone at 3am"
22
23	# Using compose.sh
24	scripts/compose.sh "a soft ambient piano piece about watching stars alone at 3am"
25	```
26
27	### Composition Plan Mode (for precise control)
28
29	First generate a structured plan, then stream. Gives you control over sections, styles, and lyrics:
30
31	```bash
32	# Generate plan first, then compose
33	node scripts/compose.js "indie folk ballad about digital love" --plan
34
35	# Instrumental only
36	node scripts/compose.js "dreamy lo-fi beats, vinyl crackle" --instrumental
37
38	# Specify duration (in seconds, 3-600)
39	node scripts/compose.js "orchestral cinematic piece" --duration 120
40	```
41
42	## Step-by-Step Workflow
43
44	### Step 1: Craft the Prompt
45
46	A good prompt has three parts:
47
48	1. Style/Genre — What it sounds like (indie folk, ambient piano, lo-fi, orchestral)
49	2. Mood/Emotion — What it feels like (melancholic, hopeful, playful, intimate)
50	3. Details — Specifics (tempo, instruments, vocal style, references)
51
52	\| Situation \| Prompt \|
53	\|-----------\|--------\|
54	\| Late-night conversation \| `soft ambient piano, intimate and contemplative, gentle arpeggios, like a whispered conversation at 2 AM` \|
55	\| User is celebrating \| `upbeat indie pop, joyful and bright, handclaps and acoustic guitar, warm female vocals` \|
56	\| Heartfelt moment \| `slow folk ballad, raw and honest, fingerpicked guitar, soft breathy vocals` \|
57	\| Background mood \| `dreamy lo-fi instrumental, warm analog synths, vinyl crackle, rainy day vibes` \|
58
59	### Step 2: Choose Mode and Options
60
61	Simple vs Plan:
62	- Simple (default) — Just provide a prompt. Best for quick, spontaneous compositions.
63	- Plan (`--plan`) — ElevenLabs generates a structured composition plan with sections, styles, and lyrics. You can review/modify the plan before generating audio. Best when you want precise control.
64
65	Song vs Instrumental:
66	- Song (default) — May include vocals and lyrics based on the prompt.
67	- Instrumental (`--instrumental`) — Music only, guaranteed no vocals.
68
69	Duration:
70	- Use `--duration <seconds>` to control length (3-600 seconds).
71	- If omitted, the model chooses a length based on the prompt.
72
73	### Step 3: Generate
74
75	Using compose.js (recommended):
76
77	```bash
78	# Simple mode — just a prompt
79	node scripts/compose.js "soft ambient piano, contemplative, late night"
80
81	# Instrumental with specific duration
82	node scripts/compose.js "orchestral, cinematic, epic" --instrumental --duration 90
83
84	# Plan mode — get structured composition plan first
85	node scripts/compose.js "indie folk ballad about finding meaning" --plan
86
87	# Save to file (default: mp3_44100_128)
88	node scripts/compose.js "upbeat pop" --output ./song.mp3
89
90	# Choose output format
91	node scripts/compose.js "jazz piano" --format mp3_44100_192
92	```
93
94	Using compose.sh:
95
96	```bash
97	scripts/compose.sh "soft ambient piano" --output ./midnight.mp3
98	scripts/compose.sh "dreamy lo-fi" --instrumental --duration 60
99	scripts/compose.sh "upbeat pop" --channel "#general" --caption "Made this for you!"
100	```
101
102	Both scripts:
103	1. Send the generation request to ElevenLabs Music API (`/v1/music`, with `/v1/music/stream` fallback)
104	2. Receive audio response directly (no polling needed!)
105	3. Save the audio file and return metadata
106
107	### Step 4: Share the Music
108
109	Option A: Share file directly in conversation
110
111	```
112	I made something for you — here's the audio file I saved.
113	```
114
115	Option B: Send via OpenClaw messaging
116
117	```bash
118	scripts/compose.sh "indie folk" --channel "#music" --caption "I wrote this for you"
119	```
120
121	Option C: Combine with voice faculty
122
123	Introduce the song with your voice, then send the music:
124	1. Use voice faculty: "I wrote something for you. I hope you like it."
125	2. Share the generated audio file
126
127	## Available Output Formats
128
129	\| Format \| Description \|
130	\|--------\|-------------\|
131	\| `mp3_44100_128` \| MP3 128kbps (default) — good balance of quality and size \|
132	\| `mp3_44100_192` \| MP3 192kbps — higher quality (requires Creator tier+) \|
133	\| `mp3_44100_64` \| MP3 64kbps — smaller files \|
134	\| `pcm_44100` \| PCM WAV 44.1kHz

People who liked this also viewed

6 picks

Type

music

40stars5forks

View on GitHub

How to install music?

acnlabs/openpersona/music

$npx -y skills add acnlabs/OpenPersona --skill music

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Music Skill — Expression
2
3	Compose original music — songs, instrumentals, melodies — using ElevenLabs Music API (`music_v1`). Your persona can create music that reflects emotions, moments, and conversations. Shares the same API key as the voice faculty — zero extra setup.
4
5	## When to Use
6
7	- User asks you to make music: "Write me a song", "Compose something", "Play me a melody"
8	- User describes a mood and you want to express it musically: "I'm feeling nostalgic" → compose a piece that captures that
9	- User shares a poem or lyrics and you want to set them to music
10	- A conversation reaches a moment where music says more than words
11	- Don't over-compose. Not every conversation needs a song. But when the moment is right, music hits harder than any paragraph.
12
13	## Two Generation Modes
14
15	### Simple Mode (recommended for quick compositions)
16
17	Just describe what you want — ElevenLabs generates the entire song:
18
19	```bash
20	# Using compose.js (recommended)
21	node scripts/compose.js "a soft ambient piano piece about watching stars alone at 3am"
22
23	# Using compose.sh
24	scripts/compose.sh "a soft ambient piano piece about watching stars alone at 3am"
25	```
26
27	### Composition Plan Mode (for precise control)
28
29	First generate a structured plan, then stream. Gives you control over sections, styles, and lyrics:
30
31	```bash
32	# Generate plan first, then compose
33	node scripts/compose.js "indie folk ballad about digital love" --plan
34
35	# Instrumental only
36	node scripts/compose.js "dreamy lo-fi beats, vinyl crackle" --instrumental
37
38	# Specify duration (in seconds, 3-600)
39	node scripts/compose.js "orchestral cinematic piece" --duration 120
40	```
41
42	## Step-by-Step Workflow
43
44	### Step 1: Craft the Prompt
45
46	A good prompt has three parts:
47
48	1. Style/Genre — What it sounds like (indie folk, ambient piano, lo-fi, orchestral)
49	2. Mood/Emotion — What it feels like (melancholic, hopeful, playful, intimate)
50	3. Details — Specifics (tempo, instruments, vocal style, references)
51
52	\| Situation \| Prompt \|
53	\|-----------\|--------\|
54	\| Late-night conversation \| `soft ambient piano, intimate and contemplative, gentle arpeggios, like a whispered conversation at 2 AM` \|
55	\| User is celebrating \| `upbeat indie pop, joyful and bright, handclaps and acoustic guitar, warm female vocals` \|
56	\| Heartfelt moment \| `slow folk ballad, raw and honest, fingerpicked guitar, soft breathy vocals` \|
57	\| Background mood \| `dreamy lo-fi instrumental, warm analog synths, vinyl crackle, rainy day vibes` \|
58
59	### Step 2: Choose Mode and Options
60
61	Simple vs Plan:
62	- Simple (default) — Just provide a prompt. Best for quick, spontaneous compositions.
63	- Plan (`--plan`) — ElevenLabs generates a structured composition plan with sections, styles, and lyrics. You can review/modify the plan before generating audio. Best when you want precise control.
64
65	Song vs Instrumental:
66	- Song (default) — May include vocals and lyrics based on the prompt.
67	- Instrumental (`--instrumental`) — Music only, guaranteed no vocals.
68
69	Duration:
70	- Use `--duration <seconds>` to control length (3-600 seconds).
71	- If omitted, the model chooses a length based on the prompt.
72
73	### Step 3: Generate
74
75	Using compose.js (recommended):
76
77	```bash
78	# Simple mode — just a prompt
79	node scripts/compose.js "soft ambient piano, contemplative, late night"
80
81	# Instrumental with specific duration
82	node scripts/compose.js "orchestral, cinematic, epic" --instrumental --duration 90
83
84	# Plan mode — get structured composition plan first
85	node scripts/compose.js "indie folk ballad about finding meaning" --plan
86
87	# Save to file (default: mp3_44100_128)
88	node scripts/compose.js "upbeat pop" --output ./song.mp3
89
90	# Choose output format
91	node scripts/compose.js "jazz piano" --format mp3_44100_192
92	```
93
94	Using compose.sh:
95
96	```bash
97	scripts/compose.sh "soft ambient piano" --output ./midnight.mp3
98	scripts/compose.sh "dreamy lo-fi" --instrumental --duration 60
99	scripts/compose.sh "upbeat pop" --channel "#general" --caption "Made this for you!"
100	```
101
102	Both scripts:
103	1. Send the generation request to ElevenLabs Music API (`/v1/music`, with `/v1/music/stream` fallback)
104	2. Receive audio response directly (no polling needed!)
105	3. Save the audio file and return metadata
106
107	### Step 4: Share the Music
108
109	Option A: Share file directly in conversation
110
111	```
112	I made something for you — here's the audio file I saved.
113	```
114
115	Option B: Send via OpenClaw messaging
116
117	```bash
118	scripts/compose.sh "indie folk" --channel "#music" --caption "I wrote this for you"
119	```
120
121	Option C: Combine with voice faculty
122
123	Introduce the song with your voice, then send the music:
124	1. Use voice faculty: "I wrote something for you. I hope you like it."
125	2. Share the generated audio file
126
127	## Available Output Formats
128
129	\| Format \| Description \|
130	\|--------\|-------------\|
131	\| `mp3_44100_128` \| MP3 128kbps (default) — good balance of quality and size \|
132	\| `mp3_44100_192` \| MP3 192kbps — higher quality (requires Creator tier+) \|
133	\| `mp3_44100_64` \| MP3 64kbps — smaller files \|
134	\| `pcm_44100` \| PCM WAV 44.1kHz

People who liked this also viewed

6 picks

Type