Building Voice-First Android Apps

Thanks to the latest advancements in Machine Learning, we're now capable of interacting with machines through natural language. The age of voice assistants is here with Alexa, the Google Assistant and others. But, as an Android developer, what can I do on my existing app in relation to conversational features?

When we think about developing features that are voice-forward, we think about existing voice assistants such as Alexa and the Google Assistant. What about the fully-capable computers that we have with us all the time, our smartphones? Some moments on our day to day lives are very well suited for voice interactions: while in a car or cooking for example. Let's not forget that voice interactions are extremely accessible, not only in a physical way (for people with dexterity or motion impediments) but also in a cognitive way (I think we all have a loved one in our lives that really struggles with technology, and people from some emerging countries have very limited access to computers and are not at ease with technology).

In this talk, I'll explain what integrations can be done on Android:
- 1st-party solutions such as the SpeechRecognizer and TextToSpeech APIs
- Other Google solutions such as ML Kit, TensorFlow and Dialogflow
- 3rd-party solutions such as Porcupine, Snips, Amazon Lex, Snowboy and PocketSphinx
- Integration with the Google Assistant via App Actions

How to pick the right mobile technology

If at the very beginning of mobile development (2008) and until recently, we only had official solutions provided by manufacturers which were considered to be serious solutions for creating mobile applications, in 2023 the possibilities have multiplied. Google and Apple have introduced solutions to realize the UI in a declarative way (Jetpack Compose, Swift UI), React Native has a large market share, Flutter continues to grow, and solutions like KMM (Kotlin Multiplatform Mobile) allow the sharing of business code between the two platforms. What solution should you start as a dev? As a business? In this talk, we will present you with elements to help you in your choice by answering the following questions: - Why and how each solution was created? On what basis? By who? - How it works ? How is the code executed? What are the technical limitations? - What are the possibilities for integrating these technologies into a new project? In an existing project? Can we mix these technologies?

Getting Started with GenAI as an Android developer

Have you been hearing about GenAI but hadn't had the opportunity to look more into it? Are you having trouble seeing how those tools can be integrated in your Android apps? Join me in this introductory session about GenAI solutions. I'll give an overview of how GenAI systems work then I'll explain the capabilities and limitations of the main solutions provided by Google, OpenAI, Mistral AI, Amazon, Microsoft and others. Other solutions such as LangChain and MediaPipe will covered as well. We'll go over some concrete demos and some notable libraries that you can use. At the end of this session, you'll have a clear overview of the current state of GenAI solutions and how you can apply them to your projects.

Given at Android Makers 2024 and Flutter Connection 2024