Text to Speech

What it is and what it does

Text to Speech service takes input from natural language

Supported Languages

Brazilian Portuguese plain text
English plain text
French plain text
German plain text
Italian plain text
Japanese plain text
Spanish plain text

and outputs them in correct cadence and intonation.

#####Available Output Voices

Brazilian Portuguese speech (1 female voice)
US English speech (choose between 3 voices: 2 female, 1 male)
UK English speech (1 female voice)
French speech (1 female voice)
German speech (choose between 2 voices: 1 female, 1 male)
Japanese speech (1 female voice)
Italian speech (1 female voice)
Castilian Spanish speech (choose between 2 voices: 1 female, 1 male)
North American Spanish speech (1 female voice)

One of the voices defined as American English(en-US): Allison (female,expressive,transformable) supports expressive SSML which uses the correct toning on supported emotions and situations(apologetic, uncertain...). Allison also supports voice transformation SSML which changes the characteristics of the voice heard with commands such as <voice-transformation type="Custom" glottal_tension="-80%">. You can play around with the demo here.

What it is for

Intended uses of Text to Speech are

Assistance tools for the vision impaired
Reading-based education tools
Mobile applications

I imagine it could also be useful while learning a new language since it uses the correct cadence, intonation and pronunciation.

How to use

IBM's website has comprehensive information on how to use the Text to Speech service. You can walk through the tutorial quite easily and start using the service.
You need to have a Bluemix subscription which is free and then you are given the necessary credentials required to use the service after providing credit card information. First one million characters of Text to Speech are free so no need to worry.
Commands and available platforms are also explained in the documentation, an easy to use executable is cURL which is linked in the tutorial.