1 00:00:00,670 --> 00:00:01,940 - Next let's take a look 2 00:00:01,940 --> 00:00:04,410 at the additional import declarations 3 00:00:04,410 --> 00:00:06,820 that we see here in lines seven through 11. 4 00:00:06,820 --> 00:00:10,920 Now as we did back in the data mining Twitter lesson 5 00:00:10,920 --> 00:00:15,700 we used a keys.py file to hide our credentials 6 00:00:15,700 --> 00:00:19,600 for interacting with the web services in this example. 7 00:00:19,600 --> 00:00:23,290 So you'll see down below whenever we need those keys 8 00:00:23,290 --> 00:00:26,796 we will refer to them as keys. and a variable name 9 00:00:26,796 --> 00:00:28,930 that's defined in that file. 10 00:00:28,930 --> 00:00:32,230 So it is critical in order to run this example 11 00:00:32,230 --> 00:00:37,230 that you modify that file and insert your own API keys. 12 00:00:37,380 --> 00:00:39,670 Now separately we're also going to be using 13 00:00:39,670 --> 00:00:44,550 the pyaudio module to enable us to record audio 14 00:00:44,550 --> 00:00:47,120 from the microphone on our system 15 00:00:47,120 --> 00:00:50,000 and we're going to be using the pydub module 16 00:00:50,000 --> 00:00:55,000 and it's sub-module pydub.playback to load and play back 17 00:00:55,160 --> 00:00:59,150 the audio files that we create in this example. 18 00:00:59,150 --> 00:01:01,484 And then finally we're going to use the built-in 19 00:01:01,484 --> 00:01:05,940 python standard library module called wave 20 00:01:05,940 --> 00:01:09,070 and basically what this is going to enable us to do 21 00:01:09,070 --> 00:01:12,670 is work with wave audio file formats. 22 00:01:12,670 --> 00:01:16,310 So wav is an audio file format that was originally 23 00:01:16,310 --> 00:01:19,750 developed by Microsoft and IBM a very long time ago 24 00:01:19,750 --> 00:01:23,970 and we'll be using that format to store the files 25 00:01:23,970 --> 00:01:28,180 that we send off to Watson's speech to text service 26 00:01:28,180 --> 00:01:30,223 for transcription purposes.