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, personalised and artistic apps. And we’re dedicated to offering you with the instruments wanted to innovate throughout the total growth stack on this evolving panorama.
This 12 months, we targeted on making AI accessible throughout the spectrum, from on-device processing to cloud-powered capabilities. Listed below are the highest 3 bulletins it’s good to 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 Equipment GenAI APIs powered by Gemini Nano, our best and compact mannequin designed and optimized for working straight on cellular units. These APIs present high-level, simple integration for widespread duties together with textual content summarization, proofreading, rewriting content material in numerous kinds, and producing picture description. Constructing on-device provides vital advantages comparable to native knowledge processing and offline availability at no extra price for inference. To start out integrating these options discover the ML Equipment GenAI documentation, the pattern on GitHub and watch the “Gemini Nano on Android: Constructing with on-device GenAI” speak.
#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 units and helps numerous frameworks like TensorFlow, PyTorch, Keras, and Jax, permitting for extra customization in apps. The platform now additionally provides improved assist of on-device {hardware} accelerators and a brand new AI Edge Portal service for broad protection of on-device benchmarking and evals. In case you are in search of GenAI language fashions on units the place Gemini Nano is just not accessible, you should 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 consumer expertise. To enhance this, we’ve launched Play for On-Gadget AI in beta. This service is designed to assist builders handle customized mannequin downloads effectively, making certain the suitable mannequin measurement and pace are delivered to every Android gadget exactly when wanted.
For extra data watch “Small language fashions with Google AI Edge” speak.
#3 Energy your Android apps with Gemini Flash, Professional and Imagen utilizing Firebase AI Logic
For extra superior generative AI use instances, comparable to complicated reasoning duties, analyzing massive quantities of information, processing audio or video, or producing pictures, you should use bigger fashions from the Gemini Flash and Gemini Professional households, and Imagen working within the cloud. These fashions are effectively suited to eventualities requiring superior capabilities or multimodal inputs and outputs. And for the reason that AI inference runs within the cloud any Android gadget with an web connection is supported. They’re simple to combine into your Android app through the use of Firebase AI Logic, which supplies a simplified, safe method to entry these capabilities with out managing your individual backend. Its SDK additionally contains assist for conversational AI experiences utilizing the Gemini Reside API or producing customized contextual visible belongings with Imagen. To study 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 may also 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 immediately
We launched a brand new open supply app, Androidify, to assist builders construct AI-driven Android experiences utilizing Gemini APIs, ML Equipment, Jetpack Compose, CameraX, Navigation 3, and adaptive design. Customers can create personalised Android bot with Gemini and Imagen by way of the Firebase AI Logic SDK. Moreover, it incorporates ML Equipment pose detection to detect an individual within the digital camera viewfinder. The complete code pattern is accessible on GitHub for exploration and inspiration. Uncover extra AI examples in our Android AI Pattern Catalog.
Selecting the best Gemini mannequin depends upon understanding your particular wants and the mannequin’s capabilities, together with modality, complexity, context window, offline functionality, price, and gadget 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!
