Google has integrated its new Lyria 3.5 music generation model directly into the Gemini app, allowing users to create music tracks without leaving the chat interface.
What Happened
The company introduced Lyria 3.5, a specialized model designed for audio generation, as a native feature within the Gemini application. This update moves music generation capabilities from standalone tools or API access into the conversational flow of Google's primary AI assistant. Users can now prompt the Gemini app to produce music, leveraging the Lyria 3.5 architecture to generate audio outputs directly in response to text instructions.
Why It Matters
Integrating Lyria 3.5 into the Gemini app signals a shift toward multimodal consolidation, where a single interface handles text, image, and audio generation. For developers and creators, this lowers the barrier to entry for AI-generated music, removing the need for separate specialized software or complex API integrations. It also positions Google to compete more directly in the generative audio space by making music creation a default feature for millions of Gemini users.
The Bottom Line
Google's inclusion of Lyria 3.5 in the Gemini app makes AI music generation accessible to a broader audience by embedding it within an existing, widely-used platform.