HotTea LiveVerified, material updates onlyUpdated Sep 4, 9:00 AM PDT

Live

Google rolls out Lyria 3.5 to Gemini worldwide and the Gemini API

Google launched Lyria 3.5 in Flow Music on July 29. Today, it rolled the music model out to Gemini users worldwide and to the Gemini API. The news is a wider rollout, not a new model debut.

First published Sep 4, 9:00 AM PDT · Last updated Sep 4, 9:00 AM PDT

What happened

Google made Lyria 3.5 available to all Gemini users on web and mobile. Developers can access it through the Gemini API and Google AI Studio. Google says the model can create tracks of different lengths from text or images, with improved vocals and arrangements. Every generated track carries a SynthID watermark.

Why it matters now

Google put a music model in its main assistant and developer tools, giving song generation a much larger user base. Google's model card says its quality and safety tests were internal. It describes the training material only as audio data, so creators still cannot see which catalogs trained the model.

Updates

What changed

Google rolls out Lyria 3.5 to Gemini worldwide and the Gemini API

Google expanded Lyria 3.5 to every Gemini user worldwide and made it available through the Gemini API. The model debuted in Flow Music on July 29, so today's news is a wider rollout, not a new model release.

Verification

Primary evidence before publication.

Social chatter can identify a lead. It does not authorize a HotTea live story.