Google has announced the release of the Lyria 3 Pro, a music-generation model. This comes just a month after the release of the basic version of the Lyria 3. The new model will allow users to create tracks up to three minutes long, as opposed to the 30-second compositions offered by the previous version.
Google has announced the release of the Lyria 3 Pro, a music-generation model. This comes just a month after the release of the basic version of the Lyria 3. The new model will allow users to create tracks up to three minutes long, as opposed to the 30-second compositions offered by the previous version.
The company said that in addition to the ability to create longer tracks, the Lyria 3 Pro model offers greater creative control and wider customization. In the query, users can now specify different elements of a musical composition, such as intros, verses, choruses and fades, as the model understands the structure of the track better than its predecessor, writes TechCrunch.
With the release of the Lyria 3, Google added music generation to the Gemini app. The Pro model also appears in the Gemini app, but only paid subscribers will have access to it. Google is also introducing the Lyria 3 Pro to its video editing app Google Vids and to ProducerAI, a generative AI music creation tool that the company acquired last month.
Additionally, Google is adding music generation capabilities to its enterprise tools with Vertex AI (in public preview), Gemini API, and AI Studio using the Lyria 3 Pro model.
Google emphasized that it used data from partners, as well as permissioned data from YouTube and Google services, to train the model. The company also noted that the model does not imitate specific artists. However, it added that if users specify an artist in their queries, the model draws “broad inspiration” from their style to create a track.
All tracks created with Lyria 3 and Lyria 3 Pro are tagged with SynthID technology to indicate that artificial intelligence was used to create that recording.
