Text-to-Speech is an essential feature of our Voice API. It empowers your applications to speak with your customers without prerecording the message, which significantly reduces your costs and allows you to easily construct the phrases to make your application super specific for the user, providing them with a perfect customer experience.
Recently we have improved the feature so that it's even easier to use now and extended the list of supported languages, dialects and voices. Now we support more than 200 voices - you surely can find which fits best your company brand!
Let's take a closer look at improvements.
To use the Text-to-Speech in your application, you should use talk NCCO action (or talk REST API operation depending on the use case). To select the appropriate language for the message, you had to learn the "voice names" we were using, for example:
To select the appropriate language for the message, you had to learn the "voice names" we were using for NCCO.
Now you don't have to operate "voice names": we have supported standard language codes, so all you have to do is set the desired language:
Voice API has supported language codes, so all you have to do is set the desired language.
Note: for backwards compatibility reasons, we have the voiceName parameter still supported, so you don't have to update any of your existing apps—unless you want to use any of the newly supported languages or voices.
For most of the languages, we have a few voices which you can use. To select a specific voice, use the new style parameter:
To select a specific voice, use the new style parameter.
How to know which style you can use? It's simple: visit our guide, play the sample greeting in all the supported styles and choose which one sounds best for you!
In the last three months, we have added:
7 new languages and dialects - now 50 total,
17 more languages with SSML support - now 44,
130 more voices - now 216!
Visit our Developer Portal to,
see Text-to-Speech guide with voice samples,
learn how to customise the spoken text with SSML,
copy Make a Call code snippet for a quick start,
check Speech Recognition guide to make your app not only speaking but also hearing what the user says
And stay tuned for more updates!
){kind=small}
Victor is a product manager for Vonage Voice API with seven years of experience in the telecom industry, and a software developer since his childhood. He is passionate about making technically complex things easy to understand and to use, by keeping powerful API self-descriptive and consistent. When not inventing and coding, he builds scale models and plays folk musical instruments.
