When you travel to countries where you don’t speak their language, Google Translate has become an invaluable tool. In most cases, you will speak to the app or type in the word to get the translation. Nowadays, with the camera feature in Google Translate, it allows you to essentially point your camera at text written in another language and then get a translation into your native one.
When I was wondering whether I can bring such camera translate feature to the web, I came across this web app “Thing Translator”. It was developed as part of Google’s AI Experiments project, it lets you point your phone (or laptop) at stuff and hear to say it in a different language.
Thing Translator Demo
Implementation
Behind the scenes, Thing Translator is using Google’s Cloud Vision and Translate APIs. In this article, I will explore further into the code, please follow me so that you can also build this cool app yourself.
# Step 1: Register Google Cloud API
Because this web app is using Google’s Cloud API, to get started, you need to set up a project in Google to enable using 2 of its API.
You might be afraid of Google would charge you for this experiment, please don’t worry, you would be free of charge for experiment:
- Google offers a $300 credit to get started with GCP for free
- The first **1,000 **request for Vision API and first 500,000 characters for Translate API is free every month
- You can cap your API usage
Google provided a step by step instruction of how to set this up, more details can be found in Google Cloud API getting started
Once you set up the API in GCP (Google Cloud Platform), copy and save the API Key to be used in the web app.
#computer-vision #machine-learning #machine-translation #artificial-intelligence #google-cloud-platform
