Google announced on Wednesday the release of Lyria 3 Pro, a music generation model that succeeds Lyria 3, released a month ago.
This new model allows users to create tracks up to three minutes long, compared to the 30 seconds offered by the Lyria 3 model.
The update represents a significant advancement in Google's ability to offer more robust and versatile music creation tools.
In addition to allowing the creation of longer tracks, the Lyria 3 Pro model offers better creative control and customization.
Users can specify musical elements such as intros, verses, choruses, and bridges, as the model better understands the structure of the tracks than its predecessor.
This customization capability opens up new possibilities for creative expression in AI-generated music production.
Google had already introduced music generation in the Gemini app with the release of Lyria 3.
The Pro model is also being rolled out in the Gemini app, but only paid subscribers will have access to it.
In addition, Google is integrating Lyria 3 Pro into its video editing app Google Vids and ProducerAI, an AI-powered music production tool that Google acquired last month.
Google is adding music generation capabilities to its enterprise tools with Vertex AI (in public preview), the Gemini API, and AI Studio through the Lyria 3 Pro model.
This expansion underscores Google's commitment to integrating AI into various platforms and services.
The initiative aims to facilitate music creation in professional and business environments.
Google emphasized that it used data from its partners and permissible data from YouTube and Google to train this model.
It also stated that the model does not imitate an artist.
However, if users specify an artist in the prompts, it takes broad inspiration from that artist to generate a track.
All tracks created using Lyria 3 and Lyria 3 Pro are marked with SynthID to denote that AI was used to create the track.
This measure seeks to provide transparency about the origin of the music.
SynthID helps distinguish AI-generated creations from traditional music productions.
Earlier this week, Spotify released new tools to allow artists to review songs released under their name, to prevent the misattribution of music by AI content creators.
Meanwhile, Deezer has launched tools to allow any streaming service to identify AI-generated music.
These initiatives reflect the industry's growing concern for authenticity and the protection of artists' rights in the age of AI.