Newsletter Subscribe
Enter your email address below and subscribe to our newsletter

Google is pushing the boundaries of creative AI once again. Since the launch of the Gemini app, users have been able to experiment with image and video generation. Now, the next frontier is here: custom music creation powered by Lyria 3, DeepMind’s latest generative music model.
Imagine asking for “a comical R&B slow jam about a sock finding their match” and hearing it come to life in seconds.
Lyria 3 builds on earlier versions with three major improvements:
Each track comes with custom cover art designed by Nano Banana, making it easy to share instantly with friends.
Creators can also explore Lyria 3 through YouTube’s Dream Track, now rolling out beyond the U.S. The model enhances Shorts soundtracks with lyrical verses or vibey backing tracks, giving creators more control over their content’s mood and impact.
All tracks generated in Gemini are embedded with SynthID, Google’s imperceptible watermark for AI‑generated content. Users can upload audio files to check if they were created with Google AI, strengthening transparency and trust.
Google emphasizes that Lyria 3 is designed for original expression, not imitation. Prompts referencing specific artists are treated as broad inspiration, with filters in place to prevent copyright violations. Users must adhere to Google’s Terms of Service and generative AI policies, which prohibit infringing on intellectual property or privacy rights.