Speaker 1: You won't believe how easy it is to convert audio or video to text with extreme accuracy in today's day and age. The tool I'm about to reveal won't just convert audio to text, but it can also translate it to a whole bunch of different languages. The best part is, this tool does it all offline on your computer. You don't have to be connected to the internet to use it once it's set up. In this video, I'm gonna take you through a three-step process and show you exactly how to use Buzz, the AI transcription and translation tool. Although it's simple to use, make sure you don't skip any part of this video, as I'll be revealing a whole bunch of important tips you can't afford to miss. Let's begin. First off, Buzz is available for Windows, Mac and Linux and can be downloaded from the GitHub page that's linked in the description of this video. Once here, navigate to the Releases tab on the right and then download the version that will run on your operating system. Once it's been downloaded, you can click on the file to open it and the installation is straightforward. If you're using Windows, you'll need to install Buzz on your computer. If you're using Windows and you get this smart screen, just click on More Info and then on Run Anyway. Once it's installed and open on your computer, you should be seeing this screen. You can record audio from your microphone directly into Buzz and have it transcribed in real time, and we'll get to that a little bit later. For now, click on the plus sign to add a file that you want to transcribe. A new window will open and you'll need to select the file that you want to have transcribed. By default, Buzz will only display audio files, but you can change that by going down to this dropdown menu and then selecting All Files. For the sake of this video, I'll be using this short audio file from one of my videos. It's worth noting that you can select more than one file at a time to be converted. Once you've selected the file you want to transcribe, you'll see this screen. Here, you'll need to choose if you want to use OpenAI's Whisper or the Hugging Face text-to-speech model. I recommend staying with Whisper by OpenAI and then using the Medium model. So far, this has been the best performing model for me as it's accurate and doesn't take too long to complete the task. Next, you'll need to select what you want Buzz to do. Transcribe, meaning to convert the audio to text, or Translate, meaning to convert the audio to text but in a different language. For this video, I'll be transcribing the audio. Next, you can select the language being spoken in the audio file, but to be honest, the AI model does such a good job detecting the language, I just leave it on Detect Language. If you're translating the audio, you'll have to select the language you want it to be translated to. In the Advanced tab, I'll just be leaving everything on Default. Lastly, we have the option to select Word Level Timings, meaning it'll create timestamps for every word, which can be useful for creators who want to create captions for short-form videos. I'll leave it all for now, and to start the process, I'll click on Run. The first time you use Buzz, it'll have to download the model you selected, but once that's been done, if you continue to use the same model, you don't need to be connected to the internet for Buzz to do the transcription or translation as the model will be saved to your computer. Once the model has finished downloading to your computer, you'll need to Once the model has finished downloading to your computer, Buzz will automatically start transcribing or translating the audio to text. Before we move on to step 3, if you're finding value from this video right now, can you give it a like? Also, let me know if this video is helpful for you in the comments below. Once it's finished, you'll see this screen. It'll display the completed job and you can open it by double-clicking on it. Here you'll see the text output being displayed, and from here you can export it to these three file types. Let's start by exporting it as a text file. You'll notice the text file has no timestamps. This'll be perfect for those of you who want to use the text in documents and so on. The next two file types, namely SRT and VTT, will both contain timestamps and will be perfect for those of you who want a subtitle track to add to videos. Most popular video editing software support SRT files and SRT files can also be uploaded to YouTube directly. Now just remember, there might still be errors in the text, so it's best practice to listen back to your audio file and make sure that the text output is correct. If you want to record audio directly from your microphone and have it transcribed in real time, you can click on the record button. Here you can choose the same settings I mentioned earlier, confirm that your microphone is selected, and then click on record. Whatever you say next will be converted to text in real time and you can export it in the same way I mentioned earlier on in the video. Personally, I wasn't able to get the real time transcription to work on my PC. I came across this post, which I'll link in the description, where you can download a GGML model and then save it in this location, which might fix the issue. I didn't test this as I would much rather just do my recordings with a free software like Audacity and then import the saved recording into Buzz. Hopefully by now you've seen how easy and simple it is to convert audio and video to text by using Buzz. If you found this video useful, remember to leave a like and comment and if you haven't done so already, subscribe and ring the bell to stay up to date with the latest and greatest free tools and other tech-related stuff brought to you by Memry.