Google’s Gemini Finally Learns to Sing with Lyria 3

Author(s): Mandar Karhade, MD. PhD. Originally published on Towards AI. DeepMind Lyrica 3 + Gemini = bringing high-fidelity audio generation to the masses; Queue the ethical questions. Google has officially integrated its Lyria 3 model into the Gemini app. Another day another news cycle dominated by generative AI, but this specific update feels different. We have spent the last year drowning in Large Language Models that can write poetry or debug code, yet the auditory realm remained somewhat of a frontier town. It was messy, experimental, and largely dominated by startups like Suno and Udio. But now the giant has awakened. The integration of Lyria 3 marks a significant advancement in Google’s Gemini app, shifting it from merely a text and image processor to a true multimedia studio. While it allows users to create high-fidelity audio, there are still limitations and ethical concerns surrounding AI-generated music, such as copyright issues and the potential for devaluing human musicianship. The user experience presents friction points, especially with constraints on audio length for free users, and questions remain about the technology’s quality and accessibility in a crowded AI music landscape. Read the full blog for free on Medium. Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor. Published via Towards AI