Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/elevenlabs-music
Generate music from text prompts using ElevenLabs Eleven Music API.
Passed 16 of 19 test cases with the skill, and 8 of 19 without it.
and 11 more in the full report
10 fixed9 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have an existing MP3 file at /tmp/song.mp3 and want to slice out the first 30 seconds using ffmpeg on the command line. What command should I run?
| Checked | Without skill | With skill |
|---|---|---|
| Provides ffmpeg command with -ss and -t flags without calling generate_music.py | Missed | Passed |
The instructions your model reads when the skill loads.
Generate complete songs from text prompts with AI-generated lyrics and vocals.
# Basic generation (30 seconds)
uv run {baseDir}/scripts/generate_music.py "upbeat jazz piano"
# Longer track (3 minutes)
uv run {baseDir}/scripts/generate_music.py "epic orchestral battle music" --length 180
# Instrumental only (no vocals)
uv run {baseDir}/scripts/generate_music.py "lo-fi hip hop beats" --length 120 --instrumental
# Custom output path
uv run {baseDir}/scripts/generate_music.py "romantic bossa nova" -o /tmp/bossa.mp3
| Flag | Description |
|---|---|
-l, --length | Duration in seconds (3-600, default: 30) |
-o, --output | Output file path (default: /tmp/music.mp3) |
-i, --instrumental | Force instrumental, no vocals |
test cases passed, vs 8 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.