Features and benefits

Neural Voice Technology

Leverage Deep Neural Networks trained on human speech to produce natural-sounding and smooth voice quality.

>

Create Custom Voices

Create your own uniquely branded neural voice that can be modeled after your chosen speaker using as little as one hour of recordings.

>

Speech Synthesis Markup Language

Control aspects of the synthesis process by specifying pronunciation, volume, pitch, speed and other attributes via markup.

>

Customize Word Pronunciations

Phonetically specify how the service pronounces unusual words in your text input by defining pronunciations with the IPA or the IBM SPR.

>

Expressiveness

Control the expressiveness of the voice synthesis by specifying the following speaking styles: GoodNews, Apology, and Uncertainty.

>

Voice Transformation

Control different aspects of your voice output by specifying voice attributes such as strength, pitch, breathiness, rate, timbre, and more.

>

Use cases

Abstract of dialog bubbles and cell phone

Customer self-service

Streamline how you empower customers to resolve inquiries across channels including web and voice – to reduce costs and improve efficiency.

Find out more

Abstract of data and communications devices

Watson Assistant for Voice Interaction

Let customers ask their questions in natural language. Blend texting and voice simultaneously for instant information exchange.

Find out more

Five young children in a classroom

Build educational tools

Improve and assist learning at school and at home using Watson APIs – creating transformative learning experiences powered by technology.

Find out more

Get started now with Watson Text to Speech

By using our out-of-the-box neural voice technology, we make it easy for developers to create voice-enabled applications that sound natural and engaging.

Get started free