Google launches Lyria 3 Pro with longer generation limits
Google launched Lyria 3 Pro, a music generation model, allowing users to create tracks up to three minutes long.
This release follows Lyria 3, which offered 30-second tracks, and expands Google’s generative AI capabilities for music creation, impacting creative professionals and paid subscribers of its AI services.
Lyria 3 Pro offers enhanced creative control and customization. Users can specify elements like intros, verses, choruses, and bridges within prompts.
The Pro model is rolling out in the Gemini app for paid subscribers. It will also integrate into Google Vids, a video editing app, and ProducerAI, a recently acquired GenAI-powered music production tool.
Google is extending music generation capabilities to its enterprise tools, including Vertex AI, the Gemini API, and AI Studio, via the Lyria 3 Pro model.
Google stated it trained the model using data from partners and permissible data from YouTube and Google. The company said the model does not mimic artists, but takes “broad inspiration” if an artist is specified in a prompt.
All tracks generated by Lyria 3 and Lyria 3 Pro are marked with SynthID to indicate AI generation.
Spotify earlier released tools for artists to review songs under their name to prevent misattribution by AI creators. Deezer also launched identification tools for AI-generated music across streaming services.