Google Launches Its “Most Advanced” AI Music Generator Yet

Google has released its “most advanced” generative AI model to date, Lyria 3, within its Gemini chatbot app. It’s available in beta for all users 18+ in English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese, with plans to incorporate more languages.

What it does:

• Users can describe a genre, mood, or memory and receive a unique, 30-second AI-generated track complete with vocals and lyrics.

• They can also upload photos or videos and watch Gemini compose a track with lyrics that fit the mood.

• In addition, the Gemini app creates custom cover art generated by its AI tool Nano Banana.

• Google says the goal of these tracks “isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself.”

Training:

• Though it doesn’t reveal the source material for its AI training, Google says it has developed the technology “responsibly in collaboration with the music community.”

• Music Business Worldwide interprets this as meaning it “uses music that YouTube and its parent company, Google, ‘have the right to use’ under their ‘terms of service, partner agreements, and applicable law.’”

• Google also claims that Lyria 3 is designed for original expression, “not for mimicking existing artists,” and has filters in place to check outputs against existing content.