Menu
Generate music using Gemini Lyria models. Use when user asks for "create music", "generate song", "background music", "soundtrack", "jingle", "audio track", "beat", or any music creation request.
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
| name | music-content |
| description | Generate music using Gemini Lyria models. Use when user asks for "create music", "generate song", "background music", "soundtrack", "jingle", "audio track", "beat", or any music creation request. |
| license | MIT |
| allowed-tools | ["generateMusicTrack"] |
Ask the user:
What do you need the music for?
- Video Background - Ambient/subtle for video content
- Intro/Outro - Short jingle for show/podcast
- Advertisement - Energetic promo music
- Full Song - Complete track with structure
- Mood Piece - Atmosphere/ambient
- Other - I'll describe
Store answer as: musicPurpose
Ask the user:
How long should the music be?
Short (Lyria 3) - Up to 30 seconds
- Best for: Intros, jingles, short clips
- Cost: $0.04 per clip
Full Length (Lyria 3 Pro) - Up to 3 minutes
- Best for: Full songs, longer videos
- Cost: $0.08 per song
Store answer as: duration and model
| Duration | Model | Cost |
|---|---|---|
| ≤30 seconds | lyria-3 | $0.04 |
| 31-180 seconds | lyria-3-pro | $0.08 |
Ask the user:
What genre or style?
- Electronic/EDM - Synths, beats, modern
- Ambient - Atmospheric, calm, minimal
- Corporate - Professional, uplifting, business
- Cinematic - Epic, orchestral, dramatic
- Acoustic - Guitar, piano, organic
- Upbeat/Pop - Catchy, energetic, fun
- Lo-Fi - Chill, relaxed, study music
- Other - I'll describe
Store answer as: genre
Ask the user:
What mood or energy level?
Energy:
- Low energy (calm, peaceful, meditative)
- Medium energy (balanced, flowing, steady)
- High energy (exciting, powerful, driving)
Mood:
- Happy/Uplifting
- Mysterious/Intriguing
- Dramatic/Intense
- Calm/Peaceful
- Melancholic/Emotional
- Energetic/Exciting
Store answers as: energy, mood
[GENRE] music for [PURPOSE].
[MOOD] and [ENERGY LEVEL].
[INSTRUMENTS/SOUNDS].
[TEMPO/RHYTHM].
[ADDITIONAL DETAILS].
Electronic/EDM:
Modern electronic music with synthesizers and driving beats.
{mood} atmosphere with {energy} energy.
Crisp drums, layered synths, and bass drops.
{bpm} BPM, suitable for {purpose}.
Ambient:
Atmospheric ambient music with ethereal textures.
{mood} and {energy} feeling.
Soft pads, subtle drones, and gentle movement.
Spacious and immersive, perfect for {purpose}.
Corporate:
Professional corporate music with uplifting tone.
{mood}, {energy} energy level.
Acoustic guitar, light percussion, and piano.
Inspiring and motivational, suitable for {purpose}.
Cinematic:
Epic cinematic orchestral music.
{mood} with {energy} intensity.
Strings, brass, and percussion building dramatically.
Movie soundtrack quality for {purpose}.
Lo-Fi:
Chill lo-fi hip hop beat with warm vinyl crackle.
Relaxed and {mood} atmosphere.
Mellow piano, soft drums, and ambient textures.
Perfect for studying or {purpose}.
Ask the user:
Do you have a reference image for the mood? (Optional - can help capture the visual atmosphere)
If provided, pass the image path to the workflow function:
const result = await generateMusicTrack({
prompt: musicPrompt,
outputPath: 'music.wav',
quality: 'standard',
durationSeconds: duration,
referenceImagePath: 'reference.jpg'
});
Show summary:
📋 MUSIC GENERATION PLAN
========================
Purpose: {musicPurpose}
Genre: {genre}
Mood: {mood}
Energy: {energy}
Duration: {duration} seconds
Model: {model}
Estimated Cost: ${cost}
Proceed? (yes/no)
Generate:
Use the pre-built workflow function — it validates the duration per quality, retries, saves the .wav, and reports cost:
import { generateMusicTrack } from '../index';
const result = await generateMusicTrack({
prompt: finalPrompt,
outputPath: 'music.wav',
quality: 'standard', // or 'pro' for full songs up to 180s
durationSeconds: duration
});
// result.data.audioPath, result.data.cost.totalCost
Upbeat corporate background music with light acoustic guitar and subtle percussion.
Positive and professional atmosphere.
Medium energy, not distracting.
Perfect for business presentations and explainer videos.
Modern electronic ambient music with soft synth pads.
Futuristic and innovative feeling.
Low to medium energy, atmospheric.
Suitable for tech product videos and demos.
Short energetic podcast intro music.
Upbeat and catchy with modern production.
Builds quickly and ends with a memorable hook.
15 seconds, suitable for show opening.
Catchy YouTube intro jingle.
Fun, energetic, and memorable.
Electronic elements with punchy drums.
5-10 seconds, instant brand recognition.
Exciting advertisement music with driving beat.
High energy, urgent, and attention-grabbing.
Modern pop/electronic hybrid.
Builds to an impactful climax.
Peaceful meditation music with gentle drones.
Calm, serene, and deeply relaxing.
Soft synthesizer pads and nature-inspired textures.
Minimal and spacious.
Epic cinematic orchestral score.
Dramatic, powerful, and emotionally stirring.
Full orchestra with soaring strings and powerful brass.
Builds from quiet to thunderous climax.
| Feature | Lyria 3 | Lyria 3 Pro |
|---|---|---|
| Max Duration | 30 seconds | 3 minutes |
| Cost | $0.04/clip | $0.08/song |
| Best For | Jingles, clips | Full songs |
| Quality | Good | Better |
MANDATORY pre-flight check that runs BEFORE any content plan or generation. Classifies the topic, verifies project/brand/product context, resolves the required reusable assets (characters, products, logos, voices) from the asset registry, and provides/generates whatever is missing — saving paths for reuse. Use whenever the user asks to plan a campaign, make a marketing plan, or create/generate any image, video, voiceover, or music.
Generate music using Gemini Lyria. Use for background music, jingles, intros, soundtracks, and complete songs WITH sung vocals — Lyria 3 sings your exact lyrics (8 languages, rap/sung delivery).
Generate images using Gemini 3 Image (Nano Banana). Use for thumbnails, carousels, infographics, social graphics, product photos.
Generate video content using Gemini Veo. Use when user asks to create video, TikTok ad, Instagram Reel, YouTube video, product video, explainer.
Generate voiceover audio using Gemini TTS. Use for narration, voiceovers, podcasts, multi-speaker dialogue.
Write the words — scroll-stopping hooks, framework-driven scripts, and platform-ready captions with hashtags. Use when the user needs hook ideas, a video/ad script, ad copy, post captions, or says "what should I post", "write a script", "give me hooks", "write the caption".