Gemini Updates: Lyria 3, Gemini 3.1, & New AI Features

by Anika Shah - Technology
0 comments

Google’s Gemini Drop: AI Music Creation and Reasoning Get a Boost

Google has released its February 2026 Gemini Drop, introducing significant updates to its AI capabilities, including advanced music generation with Lyria 3, enhanced reasoning with Gemini 3.1 Pro and Deep Think, and improvements to its image model, Nano Banana 2. These updates aim to empower users with more creative tools and sophisticated problem-solving abilities.

Lyria 3: AI-Powered Music Generation

The centerpiece of the February Drop is Lyria 3, Google’s most advanced AI music model to date. Lyria 3 allows users to generate 30-second custom soundtracks from both text prompts and images. This beta feature transforms ideas and visuals into unique musical pieces, complete with instrumentals, vocals, and lyrics. The service is designed to be respectful of copyright and artistic expression, creating tracks that are inspired by an artist’s style rather than directly imitating them. Music generated by Lyria 3 includes an imperceptible “watermark” to identify it as AI-generated.

To leverage Lyria 3, users can select “Create music” in the “Tools” dropdown menu within the Gemini app.

Gemini 3.1 Pro and Deep Think: Enhanced Reasoning Capabilities

Google similarly unveiled Gemini 3.1 Pro, a major upgrade to its core AI intelligence designed for complex tasks. Gemini 3.1 Pro demonstrates a significant leap in logic capabilities, achieving a verified score of 77.1% on the ARC-AGI-2 benchmark – more than double the performance of its predecessor, Gemini 3 Pro.

The release includes two tiers: Gemini 3.1 Pro for demanding workflows and Deep Think, a specialized reasoning mode tailored for scientific and engineering applications. Deep Think is available to Google AI Ultra subscribers.

Nano Banana 2: Improved Image Generation

The update also features Nano Banana 2, Google’s updated image model, which promises higher fidelity outputs and the ability to accurately render text in any language. This addresses a common challenge in AI image generation, where producing readable text has often been problematic.

Additional Updates

Google’s February 2026 Gemini Drop also includes Veo Templates, offering a starting point for video creation, and direct links to scientific papers within Gemini, ensuring research is backed by high-quality data.

These updates demonstrate Google’s continued commitment to advancing AI capabilities and providing users with innovative tools for creativity and problem-solving.

Related Posts

Leave a Comment