Okay, so for the STT demo, I'm here on the home page for the Speech-to-Text, and by scrolling on the sample sentences, I get to this portion of the page where I can either play some audio or record my own. Let me play this Sample 6 here:

Man: Where is Panthera tigris virgata native to?

As you can see, the page also advertises the advantages of using a custom model, which can understand better species' names in Latin. Now let me switch to the TTS part. For that, I created a simple PowerShell script, as I would like to show you how simple it is to call it from code. Here on the top, I'm just creating a new Speech Synthesizer object. On the SSML, I have two voices: one is an unaltered version with a female voice, saying: "This is a test of the Text-to-Speech API." The next phrase is the same, but I have exaggerated quite a bit a lot of the values for pause, pitch, speed and volume, so that you can see the difference. Let's play:

Woman: This is a test of the Text-to-Speech API.

Man: This is a test of the Text-to-Speech API.

As you can see, you can play quite a bit with the options of the SSML files to tailor the results to your preference. For the translation part, we will cover that in the next module, but I would like to give you an optional homework assignment, especially if you have a friend that speaks another language. Go to www.translate.it, and start a new chat. Send the link generated and ask your friend to speak in his or her native language; check what happens. Now let's take a look in the Language category of Cognitive Services.