Menu
Generate music and audio using AI. Use when the user asks to create, generate, or make music, songs, audio, melodies, tracks, or beats. Supports text-to-music with multiple models (Stable Audio, Beatoven).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Read and manage Zergboard cards, boards, and workspaces. Use when the user asks to check Zergboard, view cards, find tasks, check sprint/cycle status, manage work items, invite guests, or interact with their Zergboard boards from the CLI.
Blink Camera Skill
Order food on DoorDash for the Beck family using the DoorDash CLI (dd-cli), composing a balanced order that covers everyone's tastes and is age-appropriate for the kids, then placing it only after Idan approves the exact items, total cost, tip, card, and ETA. Use when Idan wants to order dinner/food for the family, wants a DoorDash recommendation, or says "order us food." Reads Personal/Family Food Profile.md for tastes, allergies, and rules.
Talk to Claude by voice. Records the mic, transcribes with ElevenLabs Scribe (hosted STT, no local Whisper), sends the text to Claude via the local `claude` CLI, and speaks the reply back with ElevenLabs TTS. Use when the user wants a spoken/voice conversation, voice input, or to dictate to Claude.
Create, edit, publish, schedule, and manage Substack posts. Use when the user asks to draft or publish a Substack post, list/edit their Substack drafts, schedule a post, or upload images to Substack. Supports multiple accounts/publications.
Generate audio or video of a specific person (the user) saying arbitrary text. Clones the user's voice with ElevenLabs (Professional Voice Clone) and drives a talking-head video with fal.ai audio-driven avatar models. Use when the user wants to make their voice say something, produce a talking-head video of themselves, or build/manage their voice/face twin.
| name | fal-music |
| description | Generate music and audio using AI. Use when the user asks to create, generate, or make music, songs, audio, melodies, tracks, or beats. Supports text-to-music with multiple models (Stable Audio, Beatoven). |
| allowed-tools | Bash, Read, Write |
Generate music using FAL.ai — access to Stable Audio Open, Stable Audio 2.5, and Beatoven Maestro through a single API.
Uses the same FAL API key as fal-video-skill. If not already configured:
python3 ~/.claude/skills/fal-music-skill/fal_music_skill.py config YOUR_API_KEY
Or set environment variable:
export FAL_KEY="your_api_key"
python3 ~/.claude/skills/fal-music-skill/fal_music_skill.py generate "your prompt" [OPTIONS]
Arguments:
PROMPT - Music description (e.g., "dark synthwave with driving bass and arpeggiated synths")--model, -m - Model to use (default: stable-audio-25)--duration, -d - Duration in seconds (default: 60)--steps, -s - Inference/refinement steps--guidance, -g - Guidance scale (stable-audio-25 only)--creativity - Creativity level 1-20 (beatoven only)--negative-prompt, -n - What to avoid (beatoven only)--seed - Random seed for reproducibility--output, -o - Output file path--timeout, -t - Timeout in seconds (default: 300)Examples:
# Synthwave track
python3 fal_music_skill.py generate "dark synthwave instrumental, driving bassline, analog arpeggios, 120 BPM" -d 90
# Ambient music with Beatoven
python3 fal_music_skill.py generate "ambient electronic, atmospheric pads, gentle evolving textures" -m beatoven -d 120
# Short loop with Stable Audio Open
python3 fal_music_skill.py generate "128 BPM techno drum loop with acid bass" -m stable-audio -d 30
# Custom output path
python3 fal_music_skill.py generate "epic orchestral trailer music" -o ~/music/trailer.wav
python3 ~/.claude/skills/fal-music-skill/fal_music_skill.py models
python3 ~/.claude/skills/fal-music-skill/fal_music_skill.py config
| Model | Quality | Max Duration | Cost | Best For |
|---|---|---|---|---|
stable-audio | Good | 47s | Free | Loops, SFX, short clips |
stable-audio-25 | Excellent | 190s | ~$0.20/gen | Full tracks, high quality |
beatoven | Best | 150s | Varies | Full songs, compositions |
Audio files saved to ~/.claude/skills/fal-music-skill/output/ by default.
JSON output includes:
{
"status": "success",
"model": "stable-audio-25",
"file": "/path/to/audio.wav",
"url": "https://fal.media/...",
"duration": 60,
"prompt": "..."
}
Good prompts for music generation:
requests>=2.28.0
#music #ai #fal #audio #generation