How to Convert Text to Speech Using Descript’s Overdub Stock Voices

Some links in this post are affiliate links, I may earn a commission (at no additional cost to you) if you make a purchase. Read the disclosure for more information.

In this video, I’m going to show you how you can use Descript’s Overdub stock voices to convert text to speech.

Hi, my name is David and if it’s your first time checking out my video tutorials, and you get any value from the content that you watch, kindly consider subscribing, liking this video and sharing it with people so that we can all learn at the same time.

Descript is a powerful automatic transcription software that you can use to transcribe audio and video files.

It is also a powerful podcast application that you can use to edit your podcast and record your podcast on the fly.

So for the purposes of this video, all we need to look at is something called overdub stock voices.

Now, I’m inside the project browser here and these are some of the projects that I’ve worked on in the past.

And as you can see, to my left, there’s overdub, and this is written Pro.

The overdub stock voices are free of charge to use so you can use them whether you’re on the free plan and you just want to test them out because these are automatically synthesized voices that are ready to use.

As for the overdub in this, you can actually purchase the plan and then record your voice so that you can just paste in a script.

And then you use your voice for the script instead of recreating or recording the particular voiceovers for your projects.

So that’s just to get that out of the way.

But to use overdub stock voices, you’ll need to create a new project.

The new project that you create, you can title it whatever you want.

Let’s say- Sample and then click on Create Project.

And once you click on Create Project, you’re going to get a new composition. You can title the composition, let’s say-



And then what we need to do here.

We can either just type our script, and then use the overdub stock voices.

But what I’m going to do, is that I’m going to go to my blog and just pick this first section here.

Just copy it, and then come back into Descript and just paste this inside there.

So it’s already pasted inside there.

Now what I need us to look at first is that to insert the voices you need to come to edit, and then click on Manage speakers.

From this particular section, you will add the speakers that you want.

Let’s say your script involves two people talking to each other.

Let’s say like you’re trying to simulate a phone conversation or something. Then you can add different speakers for the different scenarios.

So we’ll come to add speaker and a couple of voices and you can name or title, the speaker. You can put the speaker name and then come to this the overdub voice.

Just click on that. Let’s click on that again.

And you have a couple of voices. We have Don, Emily, Carla, Ruth, Malcolm, Ethan, Henry and Nancy.

So you can just click on this to hear the voices, the different voices and choose what fits you best.

Let’s say for example, I go with Ethan.

I just click on that, and then tick to check that particular checkbox and then click on Done.

And you can actually add the speaker name here.

Let’s say Ethan. And then click on Done.

Once you click on done, you’ll notice that our timeline down here doesn’t have the audio waveform, like what we’re already used to if you’ve used Descript.

What we need to do now is just come and click on unknown speaker.

And since this is an unknown speaker, we can come to Ethan and there are three voices that are appended to Ethan’s voices.

There is Formal 1, Formal 2, Formal 3.

Let’s just go with Formal 1. And click on that.

What is going to happen is that overdub voices are going to start generating for these particular scripts that we have here.

So the text is going to be converted into audio.

And it goes in stages depending on the paragraphs that you have.

So there we have our first voice.

It’s been inserted automatically using overdub voices.

And then you can come back to the second paragraph here.

And then let’s say if it was a conversation and you have different speakers, then you can insert the different speakers here so that the conversation can flow as you’re trying to simulate maybe a phone call or anything of that sort.

Let’s say, we still go with the same voice, Ethan, Formal 1.

And that’s also going to automatically generate the voice that we need for this.

Now once this is done, I’m going to play the audio for you so that you can hear how it sounds.

And let me know in the comments, if you can feel like there’s a difference or if this is something that you can use to convert text to speech, let’s play.

‘In this post, I’m going to show you how to transcribe audio and videos fast using easy and achievable tactics.

Audio transcription is not easy and for a veteran transcriber, it takes about four to six hours to transcribe a one hour audio file or interview.’

It’s done a pretty good job.

One thing that I’d like you to note is that anywhere there is a comma, it takes a long time to try and readjust to that.

Let’s say we go back a little bit and remove that comma.

It’s going to auto generate that particular section again.

It’s regenerated without the comma and let’s listen.

In this post, I’m going to show you how to transcribe audio and video is fast using easy and achievable tactics.

Now you can notice that now it’s flowing a little bit better.

So you’ll need to know where to use the commas, the full stops and everything else so that he can make the voice flow as it is required.

But this is a good way that anyone can use because I will have mentioned the overdub stock voices are free to use.

So you can use it to maybe convert your blog posts into audio files, so that you can keep viewers longer on your website.

It really depends on what you want to do, or even have the voiceover created from a transcript.

And then you create the different images for maybe videos on YouTube.

So I hope that this makes sense to anyone.

And once you’re done as always, you can just come to share and then come to export, export audio, current composition, yes.

And then you can choose the format that you want the audio to be in.

And then we just click on Export.

You’ll get a prompt where to save the audio and just say in the folder that you see. Let’s click on Save. And depending on the length of your audio, it may take a long or short time.

Let’s click on open.

So here’s the file.

Let’s right click on the audio and open it up with something like let’s say VLC. So let’s say VLC media player.

‘In this post, I’m going to show you how to transcribe audio and videos fast using easy and achievable tactics.

Audio transcription is not easy and for a veteran transcriber, it takes about four minutes, six hours to transcribe- (cross talk)

It’s pretty good.

Just some some few tweaks that you can do to make sure that the voice sounds as natural as possible.

So it’s pretty good that we can do this for free inside Descript.

And you can easily convert your scripts to audio files or even converts our your blog posts into audio files that people can listen to on your website when they visit and consume your blog post.

Thank you so much for watching this video and I’m so excited for this particular feature from Descript.

If you like this video kindly hit the like button, share it with your friends. And if you’re not subscribed to the channel and you got value from this video, kindly consider subscribing.

Thank you so much for watching this video.

And until next time, never stop learning.

Get Free Email Updates!

Signup now and receive an email once I publish new content.

I agree to have my personal information transfered to MailChimp ( more information )

I will never give away, trade or sell your email address. You can unsubscribe at any time.

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.