text to speech speaking styles
AI Voices,  Features,  Podcasts,  Speaking Styles,  Text to Speech

Different text to speech Speaking Styles! Now on Play.ht!

Are you looking to spice up your text to speech experience? Do you wish to change how your audio sounds, from the monotonous voice you’ve been using until now? Well look no further! With Play.ht, you can now change the speaking styles of your text to speech voices as per your need.

When people speak, they use different speaking styles depending on context. When you’re with a group of friends, your tone and style change from a regular to a more cheerful and conversational one. With the latest advancements in speech synthesis technology, you can now do just this, with AI Voices.

Incorporating all the speaking styles from Amazon Polly, Microsoft, Google Wavenet and IBM Watson, we bring the best text to speech experience for you, and your audience.

Let’s take a look at all the various styles available with each of the big names, and how you can use these voices on Play.ht to match your requirement.

Speaking Styles with Amazon Polly

Polly’s Neural TTS technology supports two speaking styles that allow you to better match the delivery style of the speaker to the application.

A Newscaster reading style that is tailored to news narration use cases, and a Conversational speaking style that is ideal for two-way communication like telephony applications.

Evaluations have shown that Polly’s newscaster voice is preferred over the neutral speaking style for voicing news content. The following histogram shows results for their Newscaster voice when compared to other voices for the news use case.

histogram shows results for their Newscaster voice when compared to other voices for the news use case.

Newscaster Speaking Style

This style can be used to synthesize speech as if it is were spoken by a TV or Radio newscaster. This can be a great way to read news articles or deliver flash briefing updates.

Listen to Amazon Polly’s Newscaster voice »

Conversational Speaking Style

This style can be used to synthesize speech to simulate the tone of a friendly conversation. The Conversational style sounds natural and amiable, and can be used for many use cases including telephony.

Listen to Amazon Polly’s Conversational voice »

Speaking Styles with Microsoft

Built on a powerful base model, Microsoft’s neural TTS voices are very natural, reliable, and expressive. Through transfer learning, the neural TTS model can learn different speaking styles from various speakers, enabling nuanced voices.

With the new styles—newscast, customer service, and digital assistant—developers can tailor the voice of their apps and services for different scenarios that fit your need.

In addition, Microsoft have also released new emotion styles in their recent update. These styles allow you to adjust voices to express different emotions to fit the context, like cheerfulness or empathy.

Newscast Speaking Style

With neural TTS voices in the newscast style, your users can enjoy listening to news or articles in a professional tone that reflects what you might hear on TV or radio newscasts.

Listen to Microsoft’s Newscast voice »

Customer Service

The customer service style features a friendly and engaging tone and is suitable for scenarios involving customer support, such as an individual checking into their flight, making a restaurant reservation, or reporting a claim.

Listen to Microsoft’s Customer Service voice »

Digital Assistant

Many customers have been using neural TTS voices for their digital assistant solutions. Microsoft has introduced two styles in this area:

The chat style for more casual, conversational bots.

The assistant style features a friendly and helpful tone, which is suitable in scenarios such as smart speakers or in-car assistants. The digital assistant voice, can be used to hear the weather forecast, search for information, navigate directions, set reminders, and more.

Listen to Microsoft’s Digital Assistant voice »

The newscast text to speech style is already being used in the Bing mobile app, check out the demo video below.

Now use different emotions with Text to Speech!

To enable you in building nuanced voices for your unique scenarios, we at Play.ht also have different emotion styles. You can access cheerful and empathetic styles for Aria’s voice, lyrical style for Xiaoxiao’s voice—which sounds heartfelt and is optimized to read prose or poetry, and calm style for Francisca’s voice (Brazilian Portuguese) etc.

Furthermore, 10 new speaking styles are available with zh-CN voice, Xiaoxiao. These new styles are optimized for audio content creators and intelligent bot developers to create more engaging interactive audios that express rich emotions. These will be added in our future updates!

List of Voices with their Styles, and Customizations on Play.ht

Here’s a list of all the voices available on Play.ht, which feature customizable speaking styles.

Voice NameLanguageSpeaking Style/Emotions
Aria (Neural)English USRegular, News(formal), News(casual), Customer service, Chat, Cheerful, Empathetic
NoahEnglish USRegular, News, Conversational
JessicaEnglish USRegular, News, Conversational
Xiaoxiao (Neural)ChineseRegular, News, Customer Service, Digital Assistant, Lyrical
Yunyang (Neural)ChineseRegular, Customer Service
Francesca (Neural)Portuguese BrazilRegular, Calm
GabriellaSpanish USRegular, News
Aria (Neural)

One of our best voices at Play.ht, with the most customizations and speaking styles. You can use Aria’s voice, for almost anything, ranging from News to Casual Conversations.

Here are a few samples, featuring Aria.

Regular
News
Customer Service
Chat
Cheerful
Empathetic

Noah

If you’re looking for a masculine voice, to power your text and articles, then Noah, is the best choice for you! From News to Conversational, Noah is the next most diverse English Voice at Play.ht.

Here are a few samples, featuring Noah.

Regular
News
Conversational

Jessica

A kind of substitute to Aria, if you like your voice to sound different. Jessica has three styles to her voice, namely, regular, conversational, and news.

Here are a few samples, featuring Jessica.

Regular
News
Conversational

Xiaoxiao (Neural)

The best female Chinese voice, at Play.ht. You can call it the Chinese version of Aria. What Aria can do in English, XiaoXiao does it better in Chinese.

Here are a few samples, featuring XiaoXiao.

Regular
News
Customer Service
Digital Assistant
Lyrical

Yunyang (Neural)

The best male Chinese voice, at Play.ht. The counterpart of Noah for English.

Here are a few samples, featuring Yunyang.

Regular
Customer Service

Francisca (Neural)

Our next on the list is Francisca, tailored for our Brazilian users. She uses two styles of speaking — regular or default, and calm.

Regular
Calm

Gabriella

The best Spanish US voice on Play.ht. She comes with two styles to her voice — regular or default, and news.

Regular
News

These are all the voices with varying speaking styles available on Play.ht. We will be adding more voices, with more customizations and styles, making your text to speech experience nothing short of amazing!

Keep an eye out for our blog to know more about our future updates, and brand new features we add for you.

What do you think of these new Speaking Styles with Text to Speech? What new features would you like to see being added to our Text to Speech converter?

Let us know in the comments section below!

10 Comments

Leave a Reply

Your email address will not be published. Required fields are marked *