Speaker 1: Hi everyone, welcome to my channel Guptaji AI with yet another video on the application of AI. Today we are diving into an exciting application of AI that is transforming your voice into text. Imagine dictating your thoughts while AI does the typing for you. Sounds cool, right? Let's jump in. First, let's clarify what speech to text is. This technology converts the spoken language into written text. It's used everywhere from virtual assistants to transcribing meetings. Today we'll use one of the specific tools that is Google speech to text to make this magic happen. Alright, let's get everything set up. For this tutorial, we'll use Google speech to text. Follow along with me. First head over to the Google account. If you don't have, you'll need to create one. It's free and easy. Once you're logged in, look for the API and services section, click on library and search for speech to text API, enable it. This lets us use the service in our project. Next we need to create credentials. Go to the credentials and click create credentials. This key is like a magic pass that lets us access the speech to text service. If you're following along, make sure to copy your API key and store in your key wallet or key pass. We'll use it in our code later. By the way, have you ever used speech to text? If you have, drop a comment and let me know about your experience. Now that we have our API set up, let's install the libraries we need to run our code. We'll be using Python for this purpose. Open your terminal or command prompt, type the following commands to install the libraries. It's a bash command that is pip install speech recognition by audio. With this bash command, you'll be able to install the speech recognition by audio. And then speech recognition is our main library for converting speech to text. And pyaudio helps capture audio from our microphone. Let's write some code. Open your favorite code editor, VS code in my case, and create a new Python file called speech to text.py. As you can see on the screen, I've named it like this, speech underscore two underscore text dot py. If you're ready, let's go ahead. First we need to import the libraries. So type this, import speech recognition as SR. Next we will initialize our recognizer at this line, recognizer equals to SR dot recognizer. This is how we initialize our recognizer. Now let's listen to our microphone. The code would be with SR dot microphone as source, print, say something, audio equals to recognizer dot lesson source. Very easy to understand it. I believe this code is very easy to understand. If you will keep the naming convention easy to understand, your code will automatically become easier to understand. Finally let's convert the audio to text. The code will be like, this is going to be our code then. Within the try block you'll put text equals to recognizer dot recognize Google, and audio will be passed as a parameter. Then you print, you said, and your text. The next command would be accept SR dot unknown value error, print, sorry I could not understand the audio. Another command, accept SR dot request error, print, could not request results, check your network connection. So these are the two error exceptions which I'm putting over here, unknown value error and the request error. Time to put our code to test, let's run the script. Make sure your microphone is on and ready to use, great. Now that we have run our script, it's time to test it out. When prompted, speak clearly into your microphone, the application should convert your speech into text. Let's see how well it works. Did you get the expected results? Share your experience in the comments. See how cool it looks, the text coming on the screen as I speak. Your application is ready. Coming to this you might face some very common issues, sometimes things don't go as planned. Let's go over a few common issues you might encounter. Number one is no audio detected. Ensure your microphone is connected and working, check if the correct microphone is selected in your settings, very important. Second is network errors, make sure you have a stable internet connection since the API requires it. Third is misrecognition, speak clearly and try to minimize background noise. You have just learned how to convert speech to text using AI, this has so many applications from making notes to creating captions. If you found this tutorial helpful, don't forget to like, subscribe and hit that notification bell icon for more exciting content. Until next time, keep exploring the amazing world of AI. Thanks for watching.