Google was announced on Wednesday which launches the Lyria 3 Pro, a music generation model, a month later Lyria 3’s release. The new model will allow users to create tracks of up to three minutes long, compared to the 30-second tracks offered with the Lyria 3 model.
The company said that in addition to allowing users to create larger pieces, the Lyria 3 Pro model will offer better creative control and customization. In the prompt, users can also specify different elements of a music track, such as intro, verses, choruses, and bridges, as the model understands the structure of the track better than its predecessor.
Google previously brought the ability to create music to the Gemini app with the release of Lyria 3. The Pro model also comes with the Gemini app, but only paid subscribers will have access to it. The company is also releasing Lyria 3 Pro in the Google Vids video editing app and ProducerAI, a music production tool powered by GenAI, which Google acquired last month.
Additionally, Google is adding music-making capability to its enterprise tools with Vertex AI (in public preview), Gemini API, and AI Studio via the Lyria 3 Pro model.
Google emphasized that it used data from its partners and permissioned data from YouTube and Google to train this model. He also said that the model does not imitate an artist. However, it said that if users specify an artist in the prompts, it takes “broad inspiration” from that artist to create a track.
All tracks created using Lyria 3 and Lyria 3 Pro are tagged with a SynthID to indicate that AI was used to create that track.
Earlier this week, Spotify released new tools that allow artists to control the songs released under their name so that AI creators don’t misattribute music. Meanwhile, Deezer has released tools that allow any streaming service to recognize AI-generated music.
