I'm thrilled to announce that my project, Snap & Speak, is now live and ready for you to try! Snap & Speak is a language learning tool that turns your world into a classroom. Just take a picture, and it uses AI to give you vocabulary, example sentences, and pronunciation guides for the language you're learning. Currently, the app is powered by the Google Gemini API, which has been an incredible tool for bringing this idea to life, especially as a solo developer learning the ropes. Looking Ahead & A Question for the Experts: As I think about future improvements, I'm really fascinated by the potential of on-device AI to make the experience even faster and potentially work offline. I was wondering if anyone could share some insights on this: How can I modify the app to use a browser's built-in AI, like Chrome's integrated Gemini model, for image analysis directly on the client side? My goal would be to perform the image recognition locally in the browser, reducing the reliance on a server-side API key and network requests. Any pointers, articles, or code examples on this topic would be immensely helpful! Please give the app a try and let me know what you think. I'd love to hear your feedback on both the app itself and my question about on-device AI. Thank you for your support
Log in or sign up for Devpost to join the conversation.