Google launches Lyria 3 Pro music generation model

Google announced on Wednesday that it will launch Lyria 3 Pro, a music generation model, a month after the launch of Lyria 3. The new model will allow users to create tracks up to three minutes long, compared to the 30-second tracks offered in the Lyria 3 model.

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

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

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

Google confirmed that it used data from its partners and permitted data from YouTube and Google to train this model. He also said that the model does not imitate the artist. However, she said that if users identify an artist in the prompts, it takes “broad inspiration” from that artist to create a piece of music.

All tracks created with Lyria 3 and Lyria 3 Pro are tagged with a SynthID tag to indicate that AI was used to create that track.

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