Google Launches Lyria 3.5 in Gemini, Trained on Licensed Content
Google deploys Lyria 3.5 in Gemini and via API, with extended availability across several in-house services. The company highlights training based on licensed content, without detailing the data used. Users have fine-tuning options and ready-to-use models to generate tracks.
Licensed Training Highlighted, No Details Published
Google specifies that Lyria was trained solely on licensed content. This approach is presented in contrast to that of Suno's music model. No specific details about the training data used for Lyria 3.5 have been disclosed.
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisissez votre rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
A Model Distributed Beyond Gemini in Several Services
Lyria 3.5 is launched in the Gemini app and accessible via API. The model is also offered in Google Flow Music, which provides additional features, in Google AI Studio for developers, and in Google Vids.
Creation Controls and Guided Models to Get Started
With Gemini, users can define the genre and style, choose different voices or instruments, and produce tracks of varying lengths, whether short or long. Examples of ambient music and personalized birthday songs are provided to simplify initial uses. According to Google, this version offers more expressive voices and richer musical arrangements than the previous one.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.