skills/music-elevenlabs/SKILL.md
Generate background music from text prompts via ElevenLabs Music API. Outputs MP3 files up to 10 minutes. Use for video soundtracks, podcast intros, ambient backgrounds.
npx skillsauth add RonanCodes/ronan-skills music-elevenlabsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate music tracks from text prompts using ElevenLabs' Eleven Music API. Outputs an MP3 file — from a 3-second jingle to a 10-minute background track.
/music-elevenlabs "upbeat electronic dance track with synth leads" [--duration <seconds>] [--output <path>]
/music-elevenlabs "calm ambient piano for a product demo video" --duration 60 --instrumental
/music-elevenlabs --plan composition.json --output soundtrack.mp3
--duration — length in seconds (3–600). Default: 30.--output — output file path. Default: /tmp/music-elevenlabs-<timestamp>.mp3.--instrumental — force instrumental output (no vocals). Default: false.--plan — path to a JSON composition plan for detailed control (mutually exclusive with text prompt).--seed — integer seed for reproducibility (only with --plan).--format — output format. Default: mp3_44100_128.if [ -z "$ELEVENLABS_API_KEY" ]; then
echo "❌ ELEVENLABS_API_KEY not set."
echo ""
echo "Get your key at: https://elevenlabs.io/app/settings/api-keys"
echo "Then set it: export ELEVENLABS_API_KEY=sk_..."
echo "Or add to: ~/.claude/.env"
exit 1
fi
PROMPT="$1"
DURATION_MS=$(( ${DURATION:-30} * 1000 )) # API takes milliseconds
INSTRUMENTAL="${INSTRUMENTAL:-false}"
MODEL="music_v1"
FORMAT="${FORMAT:-mp3_44100_128}"
OUTPUT="${OUTPUT_PATH:-/tmp/music-elevenlabs-$(date +%s).mp3}"
# Validate duration (3s–600s = 3000ms–600000ms)
if [ "$DURATION_MS" -lt 3000 ] || [ "$DURATION_MS" -gt 600000 ]; then
echo "❌ Duration must be between 3 and 600 seconds"
exit 1
fi
--plan)A composition plan gives fine-grained control over sections, tempo, and instrumentation:
{
"sections": [
{
"text": "Gentle piano intro, slow tempo, ambient feel",
"duration_ms": 15000
},
{
"text": "Build energy, add drums and bass, moderate tempo",
"duration_ms": 30000
},
{
"text": "Climax with full orchestra, fast tempo, epic feel",
"duration_ms": 20000
},
{
"text": "Wind down, return to piano, fade out",
"duration_ms": 15000
}
]
}
Section durations: 3000ms–120000ms each. Total: 3000ms–600000ms.
if [ -n "$PLAN_FILE" ]; then
# Composition plan mode
PLAN=$(cat "$PLAN_FILE")
curl -s -X POST "https://api.elevenlabs.io/v1/music?output_format=${FORMAT}" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-H "Content-Type: application/json" \
-d "$(python3 -c "
import json
plan = json.loads('''$PLAN''')
data = {
'composition_plan': plan,
'model_id': 'music_v1',
'respect_sections_durations': True
}
print(json.dumps(data))
")" \
--output "$OUTPUT"
else
# Simple prompt mode
curl -s -X POST "https://api.elevenlabs.io/v1/music?output_format=${FORMAT}" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-H "Content-Type: application/json" \
-d "$(python3 -c "
import json
data = {
'prompt': '''$PROMPT''',
'music_length_ms': $DURATION_MS,
'model_id': 'music_v1',
'force_instrumental': $INSTRUMENTAL
}
print(json.dumps(data))
")" \
--output "$OUTPUT"
fi
Note: Music generation can take 30–120 seconds for longer tracks. The API streams the response.
if [ ! -f "$OUTPUT" ] || [ "$(wc -c < "$OUTPUT")" -lt 1000 ]; then
echo "❌ Music generation failed. Response:"
cat "$OUTPUT" 2>/dev/null
exit 1
fi
DURATION_ACTUAL=$(ffprobe -v quiet -show_entries format=duration -of csv=p=0 "$OUTPUT" 2>/dev/null | cut -d. -f1)
SIZE=$(wc -c < "$OUTPUT" | tr -d ' ')
✅ Music generated
Prompt: <first 80 chars>...
Model: music_v1
Duration: <N>s
Instrumental: <true|false>
Size: <N> KB
Output: <output path>
Play: open <output path>
# Quick test — generates a 5-second jingle
export $(grep ELEVENLABS_API_KEY ~/.claude/.env)
curl -s -X POST "https://api.elevenlabs.io/v1/music" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "short cheerful jingle", "music_length_ms": 5000, "model_id": "music_v1", "force_instrumental": true}' \
--output /tmp/music-test.mp3 && \
echo "✅ API key works" && open /tmp/music-test.mp3
| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| ELEVENLABS_API_KEY | yes | — | API key from elevenlabs.io/app/settings/api-keys |
music_v1 is currently the only available model| Use Case | Prompt | Duration | |----------|--------|----------| | Video intro | "cinematic orchestral buildup, epic and inspiring" | 10s | | Podcast intro | "warm jazzy lo-fi beat with soft piano" | 15s | | Product demo | "clean modern corporate background, upbeat but subtle" | 60s | | Tutorial | "calm ambient electronic, minimal and focused" | 120s | | Trailer | "dark dramatic tension building to explosive climax" | 30s | | Outro | "gentle acoustic guitar fade out, peaceful" | 10s |
generate-video — background music for Remotion video compositionssfx-elevenlabs — layer SFX over music for full audio designtts-elevenlabs — combine narration with background musicaudio-mix — mix voice + music + SFX into a final audio tracktesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".