How to Convert Speech to Text for Free | Bill Alexander | Skillshare

How to Convert Speech to Text for Free

Bill Alexander, Web Design Professional

Play Speed
  • 0.5x
  • 1x (Normal)
  • 1.25x
  • 1.5x
  • 2x
6 Lessons (21m)
    • 1. Converting Speech to Text for Free

      2:10
    • 2. Google's Speech to Text

      3:34
    • 3. Speech to Text with Dictation.IO

      3:23
    • 4. IBM Watson's Speech to Text

      4:04
    • 5. VoiceBase Speech to Text

      5:35
    • 6. Thanks for viewing the course!

      1:47

About This Class

Converting speech to text, effectively, has always been a task that many web professionals and book publishers have dreamed of. 

Fortunately, the technology has finally matured to the point where it is actually useful (but still not perfect).

The good news is that it's not as expensive as Dragon Dictate/Naturally Speaking and actually free to use!

This course will demonstrate 4 different speech to text conversion, web based applications that were once just a dream. Take your projects to a whole new level with speech to text.

I hope you will enjoy this class and that it is useful for you and your business.

Also, please check out our other classes too:

How to Start and Run a Successful Web Design Agency

Top Insider Secrets For Making Money in the Web Design Business

All the best

--- Bill Alexander

Essential Guide to Visiting and Living in Thailand

Transcripts

1. Converting Speech to Text for Free: Hi, I'm Bill Alexander. I'm with Alpine Web media dot com And welcome to this short course on speech to text applications that you can use to help build blawg posts, create email newsletters, perhaps even write an e book quickly and easily by speaking into text rather than actually typing it all in. And if you're like me, I'm not a professional type ist by any means, So being able to dictate and have it come out as text that I can later edit is definitely something that shortens up a time span for producing content for my Web sites and so forth . So I just had a few tools that I have been using recently that I wanted to share with all of you. I used to use, uh, what was called Dragon Dictate, and it just seemed like a fairly cumbersome process. Teoh, use that program. Teoh dictate. Speech detects. So as you can see, our as we will see in this course there some fantastic programs out there that are actually free of charge and they're fairly accurate, which I was very surprised just how far speech to text accuracy has come in the past few years. So I wanted to share these with you. I'm going to be sharing them with my own clients, my Web design clients and Internet marketing customers. So I wanted to share them with you on this course and hope you enjoy them. It's a fairly short course. There are only four modules, and each one briefly demonstrates each one of these speech to text applications. So I hope you enjoy. And please add your feedback. I'd love to hear from you and I I will personally answer any questions you might have. Thank you. And hope you enjoy my course. 2. Google's Speech to Text: the first speech to text application we're going to look at the first free application is from google dot com. And of course, you can see the full address in the browser bar above. And I'm going to add that you earl within the project section of this course so that you could easily have access to go and get it. And I like to add it as a quick little bookmarks that I can get in here as quick as I can. And in this case, it's a very simple browser application. It just has a screen here with a microphone icon that which in a minute here, we're going to click on, activate it in a blink and read the lettuce. No, it's working very basic. What I really like is multiple languages. So if you're not a native English speaker, you can go through in, select your language and speak into the microphone and have it, uh, translate over to text. So let's go ahead and get started. We're gonna click on the microphone icon, period. Isn't this wonderful question Mark? This is quite an interesting application, period. I would like to demonstrate even Mawr as time permits, period. Okay, so we've gone up and stop the microphone. So now if we want a copy and paste this, we can either click here and says press control, See, to copy text. So let's do that. Bring up a note pad, window paste that in there and there we go. Now, these applications aren't perfect, but there fairly accurate. I mean, I used to use Dragon dictate and which I found even that had its glitches. But it's just amazing how some of these Web based applications are very accurate. I mean, the only thing it missed, it didn't capitalize This. So I'm gonna go in and capitalize that. But as you can see, there's my text right there. This makes it very easy. Teoh perhaps create blawg posts, email newsletters. Or you could actually write an e book by mostly doing speech to tax. So it's great applications. Minimize that. And just to show you if you want to start all over again, you just go up and refresh the browser window, and you can start, do some more and and copy paste that into your your text file. And I originally came upon this when I was looking at the Web speech a p I, which allows you to use the A p i to use it within your own Web pages and so forth. But I just found this so remarkably easy that I just decided to go with this. So this is, uh this is one of several that that I'm going to be showing you in this course. So, uh, again a really great tool, Teoh, bookmark and add to your your browser so that you can access it really quick. So that's it for the Google offering. And the next one is coming right up. 3. Speech to Text with Dictation.IO: the second free speech to text Tool we're going to take a look at is called dictation dot io, and here it is, has a little bit of advertising on it, not quite as clean as the the Google Web page. Waas. But as you can see, it does a lot like the Google APP does or the Google browser dictation page does. You can get down, select your language here. Actually, it's defaulted to the United States. Which works out well for me, actually has, ah, a little bit more features than the the the Google Speech to text start dictation. Here you can clear what you have. Save and copy appear allows you, Teoh. Add a chrome app. I just drag down a shortcut here. This is what I use and it works great for me. So I havent tried the chrome app yet, but I imagine it it would probably add something appear so basically probably the same is this So But anyway, in any case, let's give it a try and see what it does. Let's start dictation. Hello. I just wanted to try this out to see how it works, Period. Is there anything else that it can do. Question. Mark, If I was interested in this, I think it would be a great addition to my web tools. Exclamation point. Okay, so I guess this is going to do it, period. So I just hit. Stop listening. And here I am, have everything right here. So I could probably save it as a file download to text, or I could copy it in the space. I'm just gonna copy it again. I'm gonna bring up no pad. And with this application, it actually I almost prefer this over the Google version simply because it gives you just a few more options. And it seems to work very efficiently, just like Google does. And so I'm definitely keeping both of these right here on my task fire so that I can easily access them. So closed that out. And I can actually clear this right here rather than having to refresh the browser like I did in Google. So I'm gonna have to kind of give this one the edge on Google and they both seem to work. I would say equivalently as faras the quality of the dictation to text. They both seemed to do a good job. This one just seems to have a few bit a few more extras that the Google on dozen, which is very basic. So that's the second speech to text application and how we're going to go look at 1/3. 4. IBM Watson's Speech to Text: our third speech to text application actually comes from IBM. This is, uh, they're offering. With that being said, I've I've tried this one out, and this is probably my least favorite. I am showing it to you because it does have some useful features, One of which is that you can select an audio file and upload it, and it will translate the recorded audio right onto the page has to be a wave file, flak or opus. And as it says, you can drag and drop the recorded audio onto the page or use the audio samples provided Now, uh, I tried using the samples and worked really well. For instance, here we go. Let's check it out. My family absolutely fascinated by the work I'm doing with Watson, and I think they feel a personal sense of pride and satisfaction with the fact that not just technology for technology's saying its technology that's actually making a difference and changing the world. Okay, now what this does is it's giving you some word alternatives to so that if it doesn't actually translate correctly, you can you can go in and change out the words and the other thing is the words are all accurate, but notice the only punctuation is right here this very long sentence. So, uh, let's refresh this. There's no button to clear it or anything like that. So you have to actually refresh the page. Okay, Now we're gonna do our own little demo. And here's what kind of bugs me a little bit about this. So let's give it a shot here. I realized that this is an IBM offering, and it's something that's going to help Watson try to understand. But I guess I really just don't understand why I can't just say, Hey, exclamation point. See what I mean? It doesn't really let you control the punctuation, and it just kind of guesses at what would be a period or a question mark. Is that all there is? See what I mean? No question. Mark there. So on that alone, I guess I would feel more comfortable if I could add in my own punctuation just to save time editing later on, because this obviously isn't very helpful. So let's stop it. And as you can see, it got some of the words wrong. Liaison? Um, that I don't know. I'm just I'm not thrilled with this one. Uh, you may find something useful for it, and it can use multiple languages, but I just don't like the fact I can't control the punctuation on the fly. You have to edit afterwards, and obviously you have to manually go up here and copy, Open a window and paste. It's It's It's okay, but definitely not my favorite. And I don't like the fact you have to refresh it in the browser. There's nothing. Nothing fancy about it. Allow Watson to learn from this session. Well, I'd say Watson's got more learning to do as far as its application. So, uh, some of you might find a use for it. And perhaps maybe some of the foreign languages translate over better. But for me, I've got to put this at the bottom of my list, and my favorite one is coming right up 5. VoiceBase Speech to Text: Okay, Here's my favorite. It's called voice based dot com. This is the the fourth speech to text application, and this is the one I really like. I like it a lot, So I'm gonna go ahead and sign into my account. Where about lob Log in. And so what? Get logged in. You're gonna come up with a tutorial here. It gives you a quick tutorial on how to use it. So let's just quick on that really quick just to see give you a taste. You're don't you? Okay. Okay. So I'm not going to put you through that whole thing. Just going to kind of give you Ah, brief. Look around. I would urge you to go in and create an account. It's free. And it gives you as, ah, personal user up, Teoh. I believe it's 500 machine minute credits, which is this amount right here. I did not pay for this. I did not pay for it at all. It gave me this free and 500 minutes is quite a lot of time, so it's a pretty good deal. Now, here's the part I really like. Obviously you have an upload section Minds cleaned out because I did some yesterday, I uploaded. Uh, I had some video courses on YouTube, and here's here's what's really great. I downloaded my YouTube video courses as MP fours. I downloaded the video, and by clicking the upload button here, you can actually go, and you can add files. And these are the file types. I mean, this is just incredible. Not only can you upload audio files you can upload video files to, such as MP force and A V eyes and M pegs. So I uploaded about six MP four files that that I'd taken off you two. And once I uploaded them, they they all appeared in here. And then you can actually click on the buttons. I'm going to just see if I can find one really quick. Um, hopefully find it really quick. Uh, see, just to kind of give you an idea how it works, Okay? What is Twitter and how does it work? So one file queued startup load. Now, I don't really want to ah, toe waste my credit on this. So what I can do is I could save it. Now. The key thing is, you want to make sure machine transcription is selected. That's the one that, um is going to be quite inexpensive. So if you go with the human transcription is going to cost you money. So I would go with machine transcription. Unless you want to spend the money toe, have a human actually do it. And even though it says it takes like a day, uh, it only took, like, five or 10 minutes, depending on the file. So, um, cancel the upload because, OK, good, because I don't want to use up all my time on it on a big file. That was a big one, too. So maximum file sizes from uploads or four megs so gives you quite a bit to work with. But what it does is in about five or 10 minutes, you will actually get notified by email using the account you signed up with that the recording is ready and it's been transcribed, and when you log in, it's going. Teoh give you the choice to download as a PdF, copy the text and so forth. And then all you do is simply go in and edit your files, your text files and I will tell you that this isn't perfect. None of them are. You may have to go in and edit some of the punctuation. It does get some of the words wrong. So, you know, and maybe in a video we're talking a little faster like I am now. So it's It's not able. Teoh really recognize it is quickly, but this really does a great job. And I love it because I can just upload videos or audio recordings and, uh, it for for what the others dio. This is my favorite, definitely, and it really gives you a generous amount to use for free, and after that it's it's it's very inexpensive to use. So this one's definitely on my the top of my tool list, probably followed by dictation dot io if I just want to dictates something in and create a short audio file and so forth. So anyway, I hope this, uh, this helps. I hope you found it useful. And, uh, so go and get yourself an account with voice base and add it to your repertoire. You will enjoy it 6. Thanks for viewing the course!: thank you so much for taking the time to view our course on speech to text. We I certainly hope that it helps you in your business ventures, whether it's Web design, blogging. Or perhaps you're publishing a Kindle book, these four modules should be a quick and easy guide to help you get started with speech to text and save you some time. So if you did enjoy this course and we hope you did, please give us a yes vote so we can continue to provide courses like this for you in the future and we've tried to provide. The resource is down below with links and so forth, so please check those out. And also please visit Alpine Web media dot com. That's our Web design company and sign up for the email newsletter where we give a lot Give away a lot of resource is tips and information, along with the course coupons that the general public just doesn't have access to. So it's a great resource. Take advantage of it, and also be sure to check out our other courses here, and particularly if you're getting into the Web design business, take it from somebody that has 25 years of experience. This course is going to jump start you in ways that you can get started immediately rather than having to learn all the pros and cons that took us years to develop. So with that being said, thanks again and hope to see you next time. And if you have any questions, as always, just ask away and we'll get back to you as soon as possible. Thank you.