The Next Generation: Diverse Perspectives on Data and AI

Modernize at your own pace with IBM Cloud Pak for Data while keeping existing entitlements

Date: Wednesday, 18 November 2020 | Time: 9:30 AM IST | 12:00 PM SGT | 3:00 AM AEDT

-->Register now

What is Text to Speech?

With Watson Text-to-Speech, you can generate human-like audio from written text.  Improve the customer experience and engagement by interacting with users in multiple languages and tones. Increase content accessibility for users with different abilities, provide audio options to avoid distracted driving, or automate customer service interactions to increase efficiencies.

→ View Demo

Watson Assistant

IBM’s AI product that lets you build, train, and deploy conversational interactions into any application, device or channel.


Powerful real-time speech synthesis

Convert written text to natural-sounding speech using our latest neural speech synthesizing techniques.

Create Custom Voices Beta

Create a uniquely branded voice adapted to a target speaker of your choosing from as little as an hour of recordings. Premium feature only.

Data control

Maintain control and ownership of your data. IBM will not collect, store or use your data without your explicit agreement and opt-in.

Watson Text to Speech features

Enable systems to “speak” 

Develop interactive products for education, automate call center interactions, communicate directions hands-free, build engaging toys for children and more.

Customize pronunciation

Deliver a seamless voice interaction that caters to your audience with control over every word.

Go across languages and voices

Convert in English, French, German, Italian, Japanese, Spanish and Brazilian Portuguese. Detects different dialects, such as U.S. and UK English and Castilian, Latin American, and North American Spanish.

Get started on Watson Text to Speech in minutes

Find out what Text to Speech can do for your communications. Give it a try for free.