How to Create Voiceover Using Google Cloud Text to Speech (Includes Video)

Last updated - December 9, 2022

If you can’t use your own voice, how can you add narration to your videos? Through the use of AI sound processing, Google’s Cloud Text tool enables you to create natural-sounding voice-overs in only a few clicks.

Whether a major corporation or an independent author, your goal while writing is to add value to and develop relationships with your readers. For such, audio is a valuable tool. Consider the popularity of podcasts as proof.

If you prefer visual content to word, we’ve included a video with a thorough and simple demonstration of the contents of this article.

Google Cloud Text-to-Speech and WaveNet: What is it? 

Developers can create natural-sounding speech with 40+ voices, accessible in 200 languages and dialects, using Google Cloud Text-to-Speech. To offer high-fidelity audio, it combines Google’s powerful neural networks with ground-breaking WaveNet research from DeepMind.

Unlike other text-to-speech systems, a WaveNet produces speech that sounds more natural. It creates voice synthesis that emphasizes and inflects syllables, phonemes, and words in a more human-like manner. The majority of the time, users prefer WaveNet’s voice audio over that of competing text-to-speech systems. A WaveNet model builds the raw audio waveforms from scratch, unlike the majority of existing text-to-speech systems.

Now that we have covered the basics of this AI-based text-to-voice system, let us take a look at the process of setting it up.

First Method

Create a Google Cloud-based Account

Google Cloud, Google’s developer platform, includes Google Text-to-Speech. It’s a collection of services that are comparable to those provided by Microsoft Azure and Amazon Web Services. To use the text-to-speech service, you must have access to Google’s developer platform.

Create a Google Cloud-based Account

In order to create an account, click the link provided above. Once you arrive at the basic information and terms page, you may fill it in as per your specific needs. The process is very simple and includes only 3 steps before you can access the main dashboard.

Step 1: Account Information

You can choose the option that most accurately defines your organization and the country it is based in under this section. After making your selections, accept the terms and conditions to continue.

Account verification

Step 2:  Identity Verification and Contact Information

This section is very self-explanatory. You may go ahead and enter the contact details related to your company and continue on.

Identity and contact verification

Step 3: Payment Information Verification

The final step in the signing process includes verifying your credit card information. You may provide this information without any worry, as they do not automatically charge the card. If that doesn’t seem comforting enough, they do also provide a $300 complimentary credit.

payment verification

Once you have completed this process, you may move on to accessing and using the Google Cloud dashboard.

Google Cloud Services

Once you have completed the signing-in process, you will be directed to your Google Cloud accounts homepage. The homepage includes a very large array of tools and services that help with managing your business. For the sake of simplicity in the article, we will stick to the Google Text-to-Speech service.

Google Cloud dashboard

To do so, go to the search bar at the top of the screen and enter “Text-to-Speech”. From the results shown, select Cloud Text-to-Speech API.

Searching for Cloud Text-to-Speech API

On the Cloud Text-to-Speech API page, click Enable in order to get the service running. Keep in mind that the free version allows up to a million characters for WaveNet. If you wish to increase that limit, you will have to purchase the paid version for $16.

Enable Cloud Text-to-Speech API

After completing the above steps, you may access the Credentials tab by going to the Sidebar and finding it under APIs & Services.

APIs & Services settings

You will be able to verify credentials by clicking Add Credentials and entering the API Key provided to you in the designated field. Once done, click Restrict Key, as this safeguards the possibility of any security threat to your account.

Create credentials on Google Cloud

WaveNet for Chrome

As we have discussed above, WaveNet is integral to using the Text-to-Speech service. In order to use this tool, you will have to install and activate it for your Chrome browser by going to the Chrome Web Store and entering WaveNet in the search bar, or you may click the link to directly access the extension page.

WaveNet for Chrome

Once you have installed and added the extension to chrome, you may access it by clicking the extension icon on the Google Chrome taskbar on the right side of the page.

You may now go ahead and enter the API Key provided at the beginning of the process. 

Now that you have the WaveNet tool up and active, you may start by copying your text and pasting it into a Word counter so as not to cross the 1 million character count. This particular character counter has a limit of 5000 characters at a time.

Word Counter website

Select the required text and right-click. From the various options in the context menu, select WaveNet for Chrome and further select Download as MP3. You can also listen to the audio to check before downloading by clicking Start Speaking after selecting the text.

As you can see, you have just converted the text into an audio file with the AI voice and speed of your choice.

Let us move on to method number 2.

Second Method

This method is equally easy, if not more. You may start by going to the Chrome Web Store as we did in the previous method and entering Chrome Audio Capture in the search bar or by clicking the link.

Once the extension is active, you have to access the Google Cloud website and select the Products tab. 

Text-to-Speech Demo settings

Under this tab, you will find the “Put Text-to-Speech into Action” field. Go ahead and paste the text you wish to convert into the provided field. You may then select the language, Voice type, and customize the speed and pitch.

Before you click the Speak It button, open the Audio capture extension that we installed the same way as before and start the audio capture.

Put Text-to-Speech into Action settings

Once the audio is completely recorded, you may go ahead and end the recording and download it.

Now that the setup procedure is complete, check out this list of some of the best online text-to-speech services apart from the one discussed in this post.

Alternate Text-to-Speech Tools


Murf plugin

Murf creates voice-overs using text. The application turns your writing into incredibly realistic AI voices, whether you type it or upload a voice clip. The voices offered by Murf are those of skilled professional voice actors. It does a number of tests on the voices. Murf may be utilized to symbolize a brand, item, company, presentation, etc.


  • You may create voice-overs from the text using Murf. Additionally, it enables you to turn your speech into editable text that you can later alter or turn into an AI voice.
  • It is possible to match the voice-over timing with the images using Murf Studio.
  • Murf provides more than 100 believable voices in 19 different languages.
  • Additionally, it contains options for pausing, altering the narrator’s tempo, emphasizing certain points, etc.
  • Additional features include adding free background music, editing video and music, verifying the script using a grammatical checker, and many more.
  • Murf offers sophisticated team collaboration capabilities, access control, a pronunciation library, and SLA for businesses wishing to produce voice-overs at scale.

Price: Murf has four pricing tiers for its solution namely, Free, Basic at $13/month, Pro at $26/month, Enterprise at $69/month, and more.


Synthesys plugin

You may extract speech that sounds natural from texts using Synthesys. With Synthesis, you may select from a broad variety of tones, languages, male and female voices, languages, and reading rates. The creation of artificial speech that sounds realistic and may be utilized for a variety of commercial reasons only requires three stages.


  • Cloud-based software.
  • A huge collection of experienced and lifelike voices. 30 male voices and over 35 female voices.
  • Create and market countless voices.
  • UI that is incredibly user-friendly.

Price: $29/month for Audio Synthesys, $39/month for Human Studio Synthesys, and $59/ month for Audio and Human Studio Synthesys.

Amazon Polly

Amazon Polly plugin

While adding text-to-speech capabilities to your application is interesting, creating lifelike sounds with advanced AI is something special. You can have access to that using Amazon Polly.

You can design uncharted categories of speech-enabled items and develop apps that speak. You are able to speak with an unequaled level of naturalness thanks to deep learning and cutting-edge AI.


  • Voices that sound natural.
  • Speech storage and distribution.
  • Streaming in real-time.
  • Create & manage speech output.
  • Low price.

Price: For the first 12 months, the first 5 million characters are free. After that, requests for speech or Speech Marks cost $4.00 per 1 million characters.


Nearly all personal digital devices, such as PCs, smartphones, and tablets, are compatible with text-to-speech services. Any text file, including Word and Pages documents, can be read aloud. You may also read online web pages out loud.

We hope you found this information useful.

Further Reading


Please enter your comment!
Please enter your name here