Google launches Lyria 3 Pro music generation model

Google announced on Wednesday that it’s releasing Lyria 3 Pro, a music generation model, a month after Lyria 3’s release. The new model will let users create tracks up to three minutes long, as compared to the 30-second-long tracks offered with the Lyria 3 model.

The company said that, apart from allowing users to create longer tracks, the Lyria 3 Pro model will offer better creative control and customization. In the prompt, users can also specify different elements of a musical piece, such as intros, verses, choruses, and bridges, as the model understands track structure better than its predecessor.

Google previously brought music generation capability to the Gemini app with the Lyria 3 release. The Pro model is also rolling out in the Gemini app, but only paid subscribers will gain access to it. The company is also rolling out Lyria 3 Pro to its Google Vids video editing app and ProducerAI, a GenAI-powered music production tool, which Google acquired last month.

In addition, Google is adding music generation capability to its enterprise tools with Vertex AI (in public preview), the Gemini API, and AI Studio through the Lyria 3 Pro model.

Google emphasized that it used data from its partners and permissible data from YouTube and Google to train this model. It also said that the model doesn’t mimic an artist. However, it said that if users specify an artist in prompts, it takes “broad inspiration” from that artist to generate a track.

All tracks that are created using Lyria 3 and Lyria 3 Pro are marked with SynthID to denote that AI was used to make this track.

Earlier this week, Spotify released new tools to let artists review songs released under their name so that AI slop creators don’t misattribute music. Meanwhile, Deezer has launched tools to let any streaming service identify AI-generated music.