Wish you could add AI to your application but have no background in making machine learning models? Are you worried it's going to take you too much time and energy just to get started? Well, I've got great news for you.
You can enable AI in your applications in seconds. That's because Google Cloud has already done the hard work for you. And in this video, I'll show you how. Yes, it's true that it can take a long time and lots of data to build a good AI model, if you start from scratch, that is. But why reinvent the wheel when you can have the state of the art at your fingertips?
Google has a long history of publishing at the forefront of AI research, and we've made our best models available to you at the click of a button. Our pre-trained APIs give you instant access to the ultimate AI toolbox, allowing you to jump right in to building AI-powered applications without having to go through years of gathering your own data, learning the AI tech, training your own models, tuning them, retraining them. Instead, simply select from our library of machine learning APIs to access the best machine learning models in the world. These include models for computer vision, speech models that work with over 70 languages and 137 language variants, language translation models, speech transcription, sentiment analysis, speech synthesis, and so much more. The possibilities are endless.
And unlike the models that you'd build from scratch, you won't need to constantly keep them updated because we're doing that for you. These models never go out of fashion as we're constantly innovating and implementing the latest breakthroughs from DeepMind, Google Research, and AI publications. And in this video, I'm going to show you how to enable speech-to-text, a popular API that processes over a a billion voice minutes per month for our enterprise customers. But keep in mind that enabling our other APIs is also quick and easy.
We have a whole library of APIs for you to explore and build with to put your app on the leading edge of innovation. Without further ado, let's dive in. I've just started a free trial with a new account, and here I am on Google Cloud Platform dashboard. Think of that as your project's home page. We're looking at the first thing you'll see when you start up your Google Cloud console.
So how do we get that state-of-the-art speech to text API enabled? Go through this hamburger navigation menu and scroll here to Speech to Text. Click, and then you'll click Enable the API.
All right, click Enable the API, and congratulations, you're ready to start adding AI-powered speech transcription to your app. So let's create a transcription. In this demo, We'll grab a file off my laptop with a local upload. But where are we uploading it to? We'll need a storage bucket to store our files on Google Cloud.
If you've already got a project going, chances are you've already got your storage bucket set up, and you can just point to it. But in case you don't, I'll go ahead and take us through making a quick bucket in here. You can name yours whatever you like.
I'll name mine MyFirstBucketTTS and add a bunch of zeros there. Now we've got the storage bucket, and we can quickly set up our workspace from that. OK.
Select Create. Now we can do a local upload. Hit Browse. There's my sample audio file. And you can see that the information from the metadata is already read in, so there's nothing for us to fill out here.
Now what language do I speak? English. But what accent?
What dialect? Ah, I'm not so sure myself. I've lived in a lot of places, but I grew up in South Africa. So let's try South African. Good luck to you, API.
And now we can just hit Submit and see the results. Ta-da! Perfect.
It's as easy as that. And in an upcoming video, I'll show you how to do this with code so you can automate transcription for many files at once. And we'll also look at how to blend APIs together. But in the meantime, head over to our Google Cloud homepage to try it out yourself today free of charge.