Record scratch—Google's Lyria 3 AI music model is coming to Gemini today

Source: Ars Technica

Rage Against the Machine Learning

“With a simple prompt, you can generate 30 seconds of something like music.”

Credit: Google

The American poet Henry Wadsworth Longfellow called music “the universal language of mankind.” Is that still true when the so‑called music is being generated by a probabilistic robot instead of a human? We’re about to find out.

Google has announced its latest Lyria 3 AI model is being deployed in the Gemini app, vastly expanding access to AI‑generated music.

• Lyria 3 builds on earlier versions that were only available through developer‑oriented products like Vertex AI.
• It’s faster and more capable.
• To use it, select the “Create music” option in the Gemini app or web UI.
• You can describe what you want, optionally upload an image for vibe guidance, and receive a 30‑second track in seconds.

Unlike past versions, you no longer need to supply lyrics. A vague prompt is enough—the model will generate suitable lyrics (often resulting in a short “jingle”).

Each music‑creation job also includes an album‑cover‑style image generated by the Nano Banana model. Gemini ships with a pre‑loaded set of AI tracks that you can remix, and the Lyria 3 tools are coming to Google’s Dream Track toolkit for YouTube Shorts, complementing the Veo AI video options.

Sample Tracks

Below are some example prompts and the resulting styles Google shared.

“Sweet Like Plantain”

Prompt:
I’m feeling nostalgic. Create a track for my mother about the great times we had as kids and the memories of her home‑cooked plantains. Make it a fun afrobeat track with a true African vibe.

“Motown Parody”

Prompt:
Quintessential 1970s Motown soul. Lush, orchestral R&B production. Warm bassline with melodic fills, locked into a steady drum groove with crisp snare and tambourine. Vintage organ harmonic bed. Three‑piece brass section. Gritty, gospel‑tinged male tenor lead.

“Pop Flutter”

Prompt:
Wistful and airy. Soft, breathy female vocals with intimacy. Rapid‑fire drum and bass rhythm, low‑passed and softened. Deep, warm bass swells. Dreamy electric piano chords and subtle chime textures. Rainy city vibes.

“Sea Shanty”

Prompt:
An authentic a‑capella sea shanty featuring a robust male choir in a traditional call‑and‑response format. The piece relies solely on synchronized foot‑stomps on a wooden deck and sharp hand‑claps for rhythm. The lead is a weathered male baritone with a gravelly timbre, answered by a powerful male choir in rich, rugged harmony. Recorded with natural room reverb to simulate a wooden ship’s deck, the performance is energetic, communal, and entirely vocal—no instruments, just layered male voices spanning tenor, baritone, and bass.

Enjoy experimenting with Lyria 3 and see what musical worlds you can conjure with just a few words!

Sour notes

AI‑generated music is not a new phenomenon. Several companies offer models that ingest and homogenize human‑created music, and the resulting tracks can sound remarkably “real,” if a bit overproduced. Streaming services have already been inundated with phony AI artists, some of which have gathered thousands of listeners who may not even realize they’re grooving to the musical equivalent of a blender set to purée.

You still have to seek out tools like that, and Google is bringing similar capabilities to the Gemini app. As one of the most popular AI platforms, we’re probably about to see a lot more AI music on the Internet. Google says tracks generated with Lyria 3 will have an audio version of Google’s SynthID embedded within. That means you’ll always be able to check if a piece of audio was created with Google’s AI by uploading it to Gemini—similar to how you can check images and videos for SynthID tags.

Google also says it has tried to create a music AI that respects copyright and partner agreements. If you name a specific artist in your prompt, Gemini won’t attempt to copy that artist’s sound; instead, it treats the name as “broad creative inspiration.” The company notes this process isn’t foolproof, and some output might still imitate an artist too closely. In those cases, Google invites users to report the shared content.

Release details

• Lyria 3 goes live in the Gemini web interface today and should appear in the mobile app within a few days.
• Supported languages: English, German, Spanish, French, Hindi, Japanese, Korean, Portuguese (more to come).
• All users will have some access to music generation; AI Pro and AI Ultra subscribers receive higher usage limits (exact numbers not disclosed).

About the author

Ryan Whitwam is a senior technology reporter at Ars Technica, covering how Google, AI, and mobile technology continue to change the world. Over his 20‑year career he’s written for Android Police, ExtremeTech, Wirecutter, The New York Times, and more. He has reviewed more phones than most people will ever own. You can follow him on Bluesky, where you’ll see photos of his dozens of mechanical keyboards.

123 Comments