Freshen up your audio content and get noticed with customisable text-to-speech software, ​​Talkia

By Jim James, Founder EASTWEST PR and Host of The UnNoticed Entrepreneur.

In the newest episode of The UnNoticed Entrepreneur podcast, you’ll hear a different voice in the intro. It’s because I’ve decided to do a little bit of freshening up.

The challenge was that I couldn’t find anyone who was willing to do this: to voiceover for me for just 20 seconds. It was too short for anybody to be really interested; It wasn’t enough money. So, what I’ve done is to turn to a platform called Talkia, where you can make text into audio just by typing it in.

A customisable, collaborative program

With Talkia, you can generate amazing-sounding voiceovers as I’ve shown in the podcast episode.

It can also be done not just in your own language. The platform can actually translate your content into other languages for you. If you have a website and you want multilingual content all from one original source language, Talkia can do the translation.

The program is available on subscription. You can use this if you want to create voiceovers that sound like real humans or, at least, close enough. It’s great for video sales letters, educational videos for marketing videos, training videos, audiobooks, recording whole sessions of a podcast show — for whatever reason.

When you use Talkia on the internet, your files are all stored in the cloud. If you have a virtual assistant (VA) like I do, you can send them the text and they can create the audio voices for you.

This is what I did. I emailed the intro text to Alecs, my VA in the Philippines. She made the intro voiceover for me when I was driving my kids to school. By the time I finished dropping the girls off, she sent me the audio file over Messenger. With that, I can hear it and we can edit it. Then, she can load it into Descript for me.

Talkia is an advanced text-to-speech software. You can customise the voice type, the pitch, and the speed. You can also add background music as we’ve done in my podcast intro and you’ll also hear it in the outro of the show.

Actually, there are two groups of voices that you can use: WaveNet (Google) and Amazon. You may or may not know but Amazon has quite a sophisticated voice recognition software like Google. This is what you’re getting with Alexa, which is Amazon’s voice recognition software.

It also works with lots of languages such as German, French, Italian, and Arabic. I tried translating it to Arabic but it didn’t read the whole sentence and it’s not quite as I expected. But in general, it will automatically translate the content that you write in English or French, for instance, into another language.

Currently, there’s a 1,000-word limit. One thousand words are basically one A4-sized page of content. So it should be enough for pretty much anybody. What I’ve done is to take 1,000 words and make the voiceover for it. I’ve taken another 1,000 and so on and stitched them together.

Using a platform like Talkia saves a lot of time and money. First, it’s because you don’t have to go out looking for someone who wants to record something that’s 20- or 30-second long for you. Also, you can have a great deal of control then and there over the kind of voice that you want.

Essentially, you’ve got your own recording studio on your own desktop.

Creating better content through audio

Everyone knows that text is great. But audio is better than text. And video is even better than audio.

So if you have a PowerPoint presentation, you can record it on Talkia and have it narrate your presentation. Or, if you’re going to a multilingual event, you can speak in English and have Talkia translate that into a local language like Hindi or Belarusian, and have it played for other people in the audience who aren’t English speakers.

You can explain content so much more effectively and efficiently using audio. It can make you look as though you’ve got a budget — you’ll come off like a bigger, richer, and more professional company if you have audio in the same way as you’ve got video.

With Talkia, you can have audio and video for your PowerPoint, emails, website, or if you go into a tradeshow, you can have a looping presentation in multiple languages — even without hiring a freelance multilingual translator (which we all know is a hard thing to do).

I’ve just done voiceovers for an automotive client in Bahasa Indonesia, Thai, and Vietnamese. It’s taken me and my team a lot of time and money to find people who can be convincing and do the voiceover.

Voiceovers are expensive even for just about a two-minute video. If you want a regular intro for about a minute, it can cost you £80 to £90. I’m not taking anything away from the great voiceover artists who are out there; the talents out there who make a TV commercial or a cartoon come alive.

A tool like Talkia isn’t going to replace that high-end talent, but it’s going to give an alternative to anyone who doesn’t have the budget or the time for those artists to work with them.

The other thing about it is speed. If I want to get a podcast episode out today, I can use Talkia in real-time. Before, I had to send a script to someone, get it back, and receive three versions. If I don’t like them, I had to give a reply about why I don’t like them.

Many of us aren’t happy with the sound of our voices. It can also be that we have a cold or our voices sound a bit dull. You can use Talkia to do the voiceover for you like what I did for my podcast to introduce myself. It’s kind of cool because if I choose myself, it would sound a bit strange. If you have product-related content that would be better read by a woman and you’re a guy, you can have a woman voiceover and vice versa.

You can really have lots and lots of reasons why you’d want to have another voice. Another example is, if you’re young and you’re selling to older people, you’d want to sound more mature. Though there could be different reasons, what really matters is that Talkia can help you get there.

I’m lucky because I’ve got a microphone and a set-up. When I asked one person to try and record the podcast intro for me, they couldn’t get a room that was quiet enough. There was echo and background noise. Talkia can remove those.

All you have to do is to log in and utilise a very simple interface.

You can cut and paste or type in what you want to be voiced over. Then you can choose different voices and adjust the pitch and the tone. You can make it sound slower if you want it to be easily understandable. You can also make it faster. You can choose if the voice is male or female, young or old. You can also choose a voice with different regional accents (e.g. American English or French- or German-spoken English). You can also have your content spoken in local languages.

In the recent episode of The UnNoticed Entrepreneur, I played a demo of the voice of an avatar called Brian (you can check the episode’s 9:15 mark). The voice is a little bit dull but fairly sonorous. Another voice that I played is Brianna (9:49).

In the episode, I also tried translating a text into the local language, Belarusian (10:24). For that, all I did was to type an English text in the Talkia interface, press an arrow to make it go across, and choose a language to translate it to.

With this tool, I was able to create an English-language voiceover, an English voiceover with a local accent, and a local-language version. And it only took me five minutes.

A powerful tool with realistic voice

Talkia is very powerful. Forbes called it “almost indistinguishable from a human’s [voice].” TechCrunch described it as an “eerily convincing speech.” Meanwhile, The Verge said that it got “some of the most realistic human voices yet.”

Through it, you can adjust the spacing between the words, the pitch, and the tone. You can choose between Google and Amazon voice groups, and there are a large number of different voices that you can choose from there.

I’ve also found that the voices don’t all work with equal transparency. For instance, Brian’s voice sounds very good if you speed him up a little bit. The Belarusian language sounded very convincing even if I don’t edit it all. Though you’ll know that it’s not the voice’s natural language, it’s very close enough for about 90% of applications.

With Talkia, you can add in pauses, change the accent, increase the grade of the accents, add background music, and increase or reduce the volume of the voice.

On the platform, you’ll be given a track and you can drop in clips into the track. Below that you can add the music. In fact, you can add multiple tracks at once. So if you want to create a conversation of people speaking, you can use Talkia. You can have an English person, a German, and a Chinese person speaking altogether.

If you’re using animation tools like Toonly, then you can also make the voice from Talkia and drop that into your Toonly video. This is something that I’ve also worked on with quite some success as well. You can create an explainer PowerPoint in Toonly (it’s from the same group that made Talkia); then, embed your audio just by downloading and uploading the mp3 file.

I’ve been a member now for a couple of years and they continue to give fantastic software updates like compatibility. For example, you can use it with Photoshop, Toonly, Doodly (where you can make storyboards), Camtasia, and Filmora among others.

Pricing

How much does Talkia cost? It’s going to be a fraction of the cost of working with a full-time voiceover artist.

The standard is $39 a month, which gives you 1,000 words per voiceover (which is what I have). There are 102 voices (43 male, 59 female voices for youth) and 30 background music. In the case of my podcast intro, I’ve just used my own music, which I uploaded to the platform.

The $39 standard price is when you pay monthly. But if you join and pay annually, you can save nearly 50%. It only costs $20 per month or $240 per year (about £170), and you can already get pretty much unlimited access to voiceovers.

If you want to have an enterprise version, it’s $40 a month if you’ll pay annually. There, you’ll have 5,000 words per voiceover. This amounts to a long-form essay because most articles are just about 1,000 word-long. As I mentioned, I’ve also daisy-chained my articles together to make a voiceover for a 1,500-word article. I just cut and pasted the two mp3 files using a platform called Descript.

If you go for the enterprise version, you’ll get 404 voices (166 male voices that sound more like a Welsh Valley choir and 238 female voices, which could be Harlem angels). You can also use 23 voices of children or 150 background music and have commercial rights as well. The commercial rights allow you to rebroadcast what you create with that music on TV, for instance, as opposed to the standard wherein you’re not supposed to do as such.

Talkia is an excellent platform that comes from Voomly LLC, the group that made Toonly and Doodly. In the latest episode of my podcast, I’ve shared how tools like it are available for us to create great content. Sometimes, there are bottlenecks; sometimes, someone’s not available to do what we’d like to do. But these online tools are here for me and you to use.

This article is based on a transcript from my podcast The UnNoticed Entrepreneur, you can listen here.

Originally published at https://eastwestpr.com on January 20, 2022.

--

--

--

Working with the world to #getnoticed from the garden shed.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Jim James

Jim James

Working with the world to #getnoticed from the garden shed.

More from Medium

CS371p Spring 2022 Blog # 6: Jeffrey Liu

Useful Android Features that you should know about

CS 373 Spring 2022: William Eng, Week 4

HMS Kit Implementation on SoundCloud