What you need to know
- Gemini now generates 30-second songs with lyrics from text prompts or photos.
- Google’s Lyria 3 model powers the feature, handling lyrics, style control, and more realistic audio.
- Type a prompt or upload an image/video, and Gemini turns it into a share-ready song with custom cover art.
The Gemini app has taken a bold step into the realm of music creation, moving beyond its initial focus on text and images. With its latest beta launch, Gemini is now equipped to compose your next musical masterpiece. Utilizing Lyria 3, Google DeepMind’s cutting-edge generative music model, users can effortlessly craft a 30-second track complete with lyrics, all by simply providing a prompt or even a photograph.
This new feature enhances the earlier iterations in three significant ways: it automatically generates lyrics, offers greater control over style, vocals, and tempo, and produces tracks that boast a more realistic and layered sound. In essence, you don’t need to be a seasoned songwriter to create something special. Just describe the mood you’re aiming for—be it “a nostalgic afrobeat tribute to my mom’s cooking” or “a goofy R&B jam about a lonely sock”—and watch as Gemini delivers a polished mini-track in mere moments.
Moreover, this innovative capability is set to debut on YouTube Shorts, initially in the U.S. and eventually expanding globally. This integration allows for customizable backing tracks and lyrics tailored for short videos, a crucial element since audio significantly influences viewer engagement.
However, the rise of AI-generated music does raise important copyright considerations. Google assures users that Lyria 3 has been developed with a strong emphasis on copyright and partner agreements, aiming for original expression rather than imitation. When a specific artist is mentioned, Gemini draws inspiration rather than serving as a direct reference. Additionally, the platform includes filters to identify existing content, with users able to report potential infringements.
Each track generated comes with SynthID, Google’s invisible watermark designed to identify AI-generated content. Gemini’s verification tools extend to audio as well, allowing users to upload files and inquire if they were created using Google AI. The system checks for SynthID and conducts its own analysis before providing an answer.
Lyria 3 is available in the Gemini app for users aged 18 and older, supporting multiple languages including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. The launch will begin on desktop, with mobile access on the horizon. Subscribers to Google AI Plus, Pro, and Ultra will enjoy higher usage limits.
Android Central’s Take
This development represents one of the more practical advancements in AI we’ve witnessed. It’s not about replacing musicians; rather, it’s about democratizing creative expression in a manner that feels engaging rather than daunting. If you’ve ever wished for a personalized birthday song, a unique theme for your group chat, or a whimsical track to share on Shorts, you can now obtain one in seconds. For users, this translates to creativity at their fingertips, marking a promising trajectory for AI in the arts.
