Speaker 1: In this video, we're going to talk about Adobe Premiere Pro 2022's latest feature, which is to transcribe a sequence. What that allows you to do is to take audio in a sequence and transcribe it into text. Initially, it doesn't sound like, well, that's very useful, you know, you cut your sequence and you go to export it and you can transcribe it so the client can have basically a script of everything you've edited together, right? But then I thought, well, gee, there could be other applications for this. And when I did a search, I really couldn't find much. So here's my explanation of one thing I could use it for. I had a client who called me up and said, hey, I have this really long interview. And when I put it into Otter, which is a service that transcribes audio into text, it wouldn't upload if I was too long. So I said, sure. You know what? Let me try something. I took their file, I threw it into a blank sequence, and then I loaded in the transcribed sequence, which is found under text. And if you don't see it anywhere on your program, go to windows, scroll down until you see the word text. And then when you launch that, you get this window. It'll probably be bigger on the screen, but you have three choices. You can transcribe a sequence, create a new caption track, or import captions from file. We want to transcribe a sequence. There are also other choices up here. When you have the transcript, you can work with it directly there. You can create captions that can be seen on screen. If you select graphics, that allows you to work with any graphics in the sequence. But anyway, all we're really interested in today is creating a transcription from our sequence. So let's say transcribe sequence. I get a choice. Audio analysis. What track is it going to look at? Well, in this case, I have two people on two separate mics. So I want to capture both of them. So I'm going to use mix. If they were all on one mic, I would just select that particular audio track. Language. You can choose from a multitude of languages. Some of these you'll have to download from the cloud, but they are available. Once they're loaded in, it works right off your computer, so you don't have to be connected to the internet. A couple of choices below that. The important one, recognize when a different person is talking. So it'll mark them as audio one, audio two. It can be quite helpful. So I've selected that. I hit transcribe. We come over to the window. It starts processing data. This is happening all on your computer, and the speed at which this will happen depends on how fast or slow your computer is. We're looking at six minutes, five minutes, to do about 30 minutes, two audio tracks. Once it finishes, you have the entire transcription. You see it's broken into speakers three, two, one. Number one, I believe, is the person asking the questions. Anyway, you have time code, so you can follow along, and if you click on here, this is the corresponding spot on the clip. What do we want to do with this? Well, we're in text mode, and we want to export a file so we can send it to the client. So we're going to bring the file, pick where you're going to save it, click save. We go to that folder, and there is our file, and you can see time code, text, all 30 minutes of it, and it's only 29 kilobits. So you can forward this to the client. It could easily be a billable item. Anyway, I just think it's really fascinating, and I'm just happy that I can show you that little bit of it. There's a whole lot more that you can do with it, that you can actually even create captions for your program. Tell me if you like this, give us a thumbs up, leave us a comment, tell me how you would use this in your projects, and as always, thank you ever so much for watching.