Using Amazon Polly to Synthesize Lifelike Speech - Part 2

This is the second part of the tutorial on how to use Amazon Polly for lifelike speech synthesis in Python.

In the first video we discussed pre-requisites for those who would be coding along. This video is all about coding though.

One thing that I forgot to mention in the first part is that we'll also going to need pygame to play or actually speak the message. So, if you don't have it, open up a terminal or command shell and do:

pip install pygame

Here's the rationale behind the code:

• create a variable that will send a request for speech synthesis
• the variable includes: the text that will be spoken, the format of the response (mp3), and the VoiceId
• our variable holds the response, which is quite intricate
• from the response, we're only interested in the 'AudioStream' part of it
• we take that 'AudioStream' and write it as .mp3 file using the write-binary ('wb') option
• we use pygame's mixer to play the file
• once it's finished, we delete the file - for a clean exit

Please watch the video for a walk-through the code. Then, you can download the code from my github and use it deliberately (I'd appreciate if you link back though).

---

Here's the first part:

1. Using Amazon Polly to Synthesize Lifelike Speech - Part 1

---

---

To stay in touch with me, follow @cristi

---

Cristi Vlad, Self-Experimenter and Author