Google DeepMind 5

AI music generator in Gemini using text, image, and video prompts. Lyria 3 is the latest AI music generation model from Google DeepMind, integrated directly into the Gemini app. Launched in February 2026, it represents a significant leap from its predecessors by offering multimodal capabilities, allowing users to generate 30-second music clips using text, images, or video context. The model automates complex musical tasks such as lyric writing and song structuring (including intros, verses, and choruses). It also incorporates SynthID watermarking for audio provenance and safety. While Lyria 3 is the primary consumer-facing tool in Gemini, the Lyria 2 model remains the enterprise standard for developers via Vertex AI API.

Google DeepMind's AI for creating full-length, high-fidelity songs from text or images. Lyria 3 Pro is Google DeepMind's flagship AI music generation model designed to create high-fidelity, full-length songs up to 3 minutes long. It features structural awareness, allowing users to generate complete compositions with specific sections like intros, verses, choruses, and bridges. The tool supports both text-to-music and image-to-music generation, providing professional-grade 48kHz stereo audio with natural-sounding vocals, lyrics, and instrumentals across various genres and styles.

Google DeepMind's SOTA image generation and editing model. Nano Banana Pro is Google DeepMind's state-of-the-art image generation and editing model, built on Gemini 3 Pro. It enables users to create, blend, and edit images with crisp text rendering, advanced reasoning, and professional controls for lighting, camera, and 4K output. It allows for rendering readable text, blending multiple references, and directing lighting, camera, and composition with studio-grade control. Nano Banana Pro is an independent product utilizing the Google DeepMind Official API and is not affiliated with Google.

Google DeepMind's flagship multimodal AI with 1M context. Gemini 3 Pro is Google DeepMind’s flagship multimodal AI, announced for preview on Nov 18–19, 2025. It features a 1M-token context window, PhD-level reasoning with Dynamic Thinking and a future Deep Think mode, and advanced agentic coding capabilities. Built on a transformer architecture, it natively ingests text, images, video, audio, and PDFs, outputting long-form text and code with advanced tool calling and structured outputs. It is purpose-built as Google’s most intelligent model for agentic tasks and “vibe coding,” enabling users to plan, learn, and build creative code-driven experiences across various modalities.

AI-powered tool for generating UIs for mobile and web apps. Stitch is an AI-powered tool designed to help application builders generate high-quality user interfaces for mobile and web applications. It facilitates fast and easy design ideation and allows users to easily export designs to Figma or directly access the frontend code. Stitch leverages some of the latest AI models from Google DeepMind.