Google's AI Music Maker Is Coming To the Gemini App

Source: Slashdot

Overview

Google is bringing its Lyria 3 AI music model into the Gemini app, allowing users to generate 30‑second songs from text, images, or video prompts directly within the chatbot. The Verge reports that Lyria 3’s text‑to‑music capabilities let Gemini users create songs by describing specific genres, moods, or memories—for example, asking for an “Afrobeat track for my mother about the great times we had growing up.”

Features

• Text‑to‑Music: Generate instrumental audio or full songs with automatically composed lyrics based on user prompts.
• Multimodal Input: Users can upload photographs and video references; Gemini uses these to generate a track with lyrics that fit the vibe.
• Custom Cover Art: Songs created in the app receive cover art generated by Nano Banana, making them easier to share and download.
• Integration with YouTube: Lyria 3 is also being added to YouTube’s Dream Track tool, enabling creators to make custom AI soundtracks for Shorts.

“The goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself,” Google said in its announcement blog.

Copyright Considerations

Dream Track and Lyria were initially demonstrated with the ability to mimic the style and voice of famous performers. Google emphasizes that it has been “very mindful” of copyright in developing Lyria 3. The tool is designed for original expression, not for mimicking existing artists. When prompted for a specific artist, Gemini will produce a track that “shares a similar style or mood” and applies filters to check outputs against existing content.