Let's begin with Text to Speech processing.
The basic process for getting the computer to speak is relatively easy:
- Produce the text of what you want to say
- Send the text to the Text to Speech service to generate a sound file
- Play the sound file through the computer's speaker
Let's walk through this process; we'll start by getting the computer to say something such as, I'm so glad you're here with me today.
Throughout this chapter, the sample applications will use the json library to facilitate printing out JSON structures. In addition, we use the TextToSpeechV1 and SpeechToTextV1 packages from the ibm_watson SDK library. You will see these included as import statements at the beginning of the sample programs.
- Building on what we have learned in Chapter 1, Background, Transition, and the Future of Computing, Chapter...