I know the title is cliche…. but my homework assignment this week for my AWS class involving using Amazon Polly. Prior to doing my homework, I had only heard that Polly existed, but I did not know anything about it. My experience with speech synthesis by computer started in elementary school. I used to write programs to speak out my spelling words, and than I would have to type in the correct spelling of the word. It randomly asked me to spell the list of words, and I would have three changes to spell each word. And, since I was young, I used to have it randomly pick background colors so that the screen would look different each time I spelled a word. My final step of geeky competitiveness was that it would provide a grade at the end of each test. Each week I would swap in my new spelling words, and make small tweaks to the program. The one thing that I could not change was the horrible sound of the voice! If I had Amazon Polly in elementary school, my spelling word program would have not only been the prettiest – but also the best sounding!
As it turns out, Polly speaks 47 languages and has both male and female voices. You can download the spoken words into an MP3 file, or cache it to use later. Of course, you can use it as many times as you like. It’s billed by the character, and it costs about four dollars for one-million characters. Depending on the use case, that isn’t too bad. I am already thinking about incorporating it into my birthday bot — how much more fun to have it talking — although that’s probably not going to happen until version 6 or 7!! We’ll see.