How to Create Custom Ad Music With AI (Artlist Lyria)
As AI music generators like Suno face strict character limits, combining LLMs with tools that accept massive descriptive prompts offers filmmakers unprecedented control over custom commercial soundtracks.
What this lesson covers
This video explores Artlist's Lyria for generating custom ad music using ultra-long text prompts. The creator demonstrates how to use Gemini to analyze reference tracks from commercials to build detailed musical prompts.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 00:46 ↗
Lyria's massive prompt capacity allows for ultra-specific control over styles, first bars, verses, and choruses.
- 01:15 ↗
Suno suffers from strict character limitations, often cutting off prompts exceeding 500 characters despite higher theoretical limits.
- 03:36 ↗
You can copy reference commercial links and paste them into Gemini with a structured prompt to break down the mood, feel, genre, and timeline.
- 06:52 ↗
Vimeo serves as a useful source of commercial inspiration where clips can be downloaded and analyzed directly within multimodal LLMs.
Workflow outlined in the video
- Find a commercial or reference track whose mood and style match your desired project.
- Paste the reference into Gemini along with a structured prompt requesting a detailed breakdown of genre, subgenre, mood, and instrumentation.
- Take the generated detailed breakdown and input it into Artlist Lyria without character constraint fears.
- Generate multiple variations in Lyria and test them directly within your edit to evaluate the practical fit.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
How to interpret the numbers
412 views captured 24 October 2026. ReelStack recommendation score: 10/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.13× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 29% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 73/100; likes + 4× comments, smoothed with a 500-view neutral prior