Google’s new Lyria 3.5 model promises richer, more emotional music

Last week, Google announced the launch of Gemini 3.6 Flash, the company’s latest workhorse Flash model. Along with 3.6 Flash, the tech giant also released Gemini 3.5 Flash-Lite and 3.5 Flash Cyber. This week, another new Google-made AI model is getting rolled out. Unlike the others, this one is aimed at helping you create music.

Google has announced that it has launched its latest music generation model, Lyria 3.5. Compared to the previous model, Lyria 3.5 is said to produce richer and more complex melodic structures. The AI is also said to adhere to prompts better and is more structurally aware, allowing it to generate higher-quality lyrics. Another improvement is vocals, which Google says are more realistic and emotionally nuanced than before, with better pronunciation to boot.

Along with these enhancements, the new model makes control over your generated music easier. Specifically, you’ll have more creative control over the tempo and duration of your songs.

Google states that Lyria 3.5 is rolling out today. You’ll find the new music generation model in Google Flow Music. In the video above, you can check out an example of a song generated by the model.