Speaker 1: Hello and welcome to Startup Hack. Today we are going to talk about convert audio to text with .NET and Azure. So let's jump right in.

Speaker 2: Make sure to check out the link down below because we always provide the code samples that you can pull down and follow along so you can see in our project.

Speaker 1: Alright speech to text technology also known as automated transcriptions is a cutting edge tool that converts spoken language into written text. Speech service captures the spoken word through a microphone, process that audio digitally and translate it into text form. It's used at business meetings, education, legal and medical fields, accessibility, customer services. So what are the prerequisites? Audience level, beginners to intermediate level readers, technical needs, a computer with internet access, a microphone and an Azure account. And the technical skills are basic understanding of cloud services, understanding of APIs along with .NET. These prerequisites are designed to ensure that readers have the necessary background to comfortably follow along with the technical content, set up the service in Azure, write and understand the C sharp code and successfully implement the speech to text feature in application. So as you can see in the picture, the microphone will transcribe from Azure speech to text. Now let's start by creating an Azure account. I have already done Azure account and I have to find speech services and create a new one. Do you want to earn $100,000 a year? Do you want to become a software developer within just three months? With our amazing course and awesome tutors, you never have to worry about getting stuck. We help students to learn skills that companies want to hire. We are startup hack. Don't forget to subscribe our channel. So let's get started. Right. So my speech services is created and it is named as speech to text over here and they have two keys, key one and key two. Also the region which will be used in our C sharp code. Also the endpoint as well. I create a new

Speaker 3: .NET console application project in Visual Studio and install this and you get package Microsoft.CognitiveServices.Speech and click enter. So once you install the package from and you get package manager, Microsoft.CognitiveService.Speech, you have to use this code. By recognizing your microphone and convert it into text. So replace your subscription key and region

Speaker 1: from here. Microsoft.CognitiveServices.Speech and you get package provides unnecessary functions to integrate as your speech services into your .NET application. It's used for connecting to the service, configuring the speech recognition and processing the results. The speech config object organized, initialized with your subscription information, which is essential for authenticating your request to the server service. The speech recognizer object is responsible for capturing audio from your microphone and sending it to the service for recognition. The recognized once async method captured a single spoken phrase and returns the results asynchronously. The result is then checked to determine if the speech was recognized successfully and if so, the recognized text is printed. I am going to run this application and when it say something prompt in the console app, I will say hello world. So let's run this application, hello world, see it is recognizing my text. Thank you for watching this video. I hope you learned how to integrate Azure's speech to text capabilities in your .NET application. You can further explore the Azure CognitiveServices Speech SDK to add more functionalities such as continuous recognition, language understanding and custom speech models. So don't forget to subscribe our channel and hit the bell icon for latest updates. To joining our course you can simply go to our website called startuphack.com Thank you.