Google's pretrained models can be used to perform predictions without us needing any knowledge of how ML works. All of the models are accessible using APIs and can be directly consumed from your application. The data for prediction is delivered using a JSON file or is stored on Cloud Storage. There are currently a number of models available, as follows:
- The Cloud Speech-to-Text API
- The Cloud Text-To-Speech API
- Google Cloud Translation API
- Cloud Natural Language API
- Cloud Vision API
- Cloud Video Intelligence API
Let's have a quick look at each of them.