Posted by Kateryna Semenova – Sr. Developer Relations Engineer
AI is reshaping how customers work together with their favourite apps, opening new avenues for builders to create clever experiences. At Google I/O, we showcased how Android is making it simpler than ever so that you can construct sensible, customized and inventive apps. And we’re dedicated to offering you with the instruments wanted to innovate throughout the total improvement stack on this evolving panorama.
This yr, we centered on making AI accessible throughout the spectrum, from on-device processing to cloud-powered capabilities. Listed here are the highest 3 bulletins you could know for constructing with AI on Android from Google I/O ‘25:
#1 Leverage the effectivity of Gemini Nano for on-device AI experiences
For on-device AI, we introduced a brand new set of ML Package GenAI APIs powered by Gemini Nano, our best and compact mannequin designed and optimized for operating instantly on cell gadgets. These APIs present high-level, straightforward integration for widespread duties together with textual content summarization, proofreading, rewriting content material in numerous kinds, and producing picture description. Constructing on-device gives vital advantages corresponding to native information processing and offline availability at no further price for inference. To start out integrating these options discover the ML Package GenAI documentation, the pattern on GitHub and watch the “Gemini Nano on Android: Constructing with on-device GenAI” discuss.
#2 Seamlessly combine on-device ML/AI with your individual customized fashions
The Google AI Edge platform permits constructing and deploying a variety of pretrained and customized fashions on edge gadgets and helps varied frameworks like TensorFlow, PyTorch, Keras, and Jax, permitting for extra customization in apps. The platform now additionally gives improved assist of on-device {hardware} accelerators and a brand new AI Edge Portal service for broad protection of on-device benchmarking and evals. If you’re searching for GenAI language fashions on gadgets the place Gemini Nano isn’t accessible, you need to use different open fashions by way of the MediaPipe LLM Inference API.
Serving your individual customized fashions on-device can pose challenges associated to dealing with massive mannequin downloads and updates, impacting the person expertise. To enhance this, we’ve launched Play for On-Machine AI in beta. This service is designed to assist builders handle customized mannequin downloads effectively, making certain the correct mannequin measurement and pace are delivered to every Android machine exactly when wanted.
For extra info watch “Small language fashions with Google AI Edge” discuss.
#3 Energy your Android apps with Gemini Flash, Professional and Imagen utilizing Firebase AI Logic
For extra superior generative AI use circumstances, corresponding to complicated reasoning duties, analyzing massive quantities of knowledge, processing audio or video, or producing photographs, you need to use bigger fashions from the Gemini Flash and Gemini Professional households, and Imagen operating within the cloud. These fashions are nicely fitted to situations requiring superior capabilities or multimodal inputs and outputs. And for the reason that AI inference runs within the cloud any Android machine with an web connection is supported. They’re straightforward to combine into your Android app by utilizing Firebase AI Logic, which offers a simplified, safe solution to entry these capabilities with out managing your individual backend. Its SDK additionally consists of assist for conversational AI experiences utilizing the Gemini Reside API or producing customized contextual visible property with Imagen. To be taught extra, try our pattern on GitHub and watch “Improve your Android app with Gemini Professional and Flash, and Imagen” session.
These highly effective AI capabilities can be delivered to life in immersive Android XR experiences. You will discover corresponding documentation, samples and the technical session: “The longer term is now, with Compose and AI on Android XR“.
Get impressed and begin constructing with AI on Android as we speak
We launched a brand new open supply app, Androidify, to assist builders construct AI-driven Android experiences utilizing Gemini APIs, ML Package, Jetpack Compose, CameraX, Navigation 3, and adaptive design. Customers can create customized Android bot with Gemini and Imagen by way of the Firebase AI Logic SDK. Moreover, it incorporates ML Package pose detection to detect an individual within the digicam viewfinder. The total code pattern is accessible on GitHub for exploration and inspiration. Uncover further AI examples in our Android AI Pattern Catalog.
Choosing the proper Gemini mannequin relies on understanding your particular wants and the mannequin’s capabilities, together with modality, complexity, context window, offline functionality, price, and machine attain. To discover these issues additional and see all our bulletins in motion, try the AI on Android at I/O ‘25 playlist on YouTube and take a look at our documentation.
We’re excited to see what you’ll construct with the ability of Gemini!
