New Training: Integrate Amazon Polly Voiceovers to Your Business Applications with Python
In this 7-video skill, CBT Nuggets trainer Trevor Sullivan explores how to leverage Amazon Polly, a managed text-to-speech (TTS) service that can generate audio content, using the Python programming language and the Boto3 module for AWS. Watch this new AWS training.
Watch the full course: AWS Cloud Automation
This training includes:
- 7 videos
- 1.2 hours of training
You’ll learn these topics in this skill:
- Introduction to Amazon Polly and Python Boto3 Module
- Set up Container Development Environment for Python and Amazon Polly
- Configure AWS Credentials for Amazon Polly APIs
- Overview of Amazon Polly REST APIs and Boto3 Module
- Synthesize Speech with Amazon Polly and Python Boto3
- Use Speech Synthesis Markup Language to Customize Amazon Polly
- Import Custom Lexicons for Amazon Polly using Python
Why Would You Use AWS Polly with Python?
Amazon's Polly service is a great way to add accessibility features to websites, applications, and services. Polly can take text, like a blog post article, and create an audio version of that text. Of course, due to the dynamic nature of websites today, it is very difficult to pre-record all of the text-based assets for a web property. Thankfully, it is easy to create a programmatic way to handle this through Python with Polly.
Before getting started with Polly using Python, developers need to download the Boto3 package with Pip (Python's package manager). Boto3 integrates the AWS SDK into Python. It is provided directly by AWS and is not a third-party package.
Once Boto3 is installed and configured, an object needs to be instantiated against a Boto3 client with Polly. Once that object is created, text can be submitted directly to Polly and then retrieved for use. The Boto3 package also includes the ability to add various lexicons to Polly on the fly, so if the text being used with Polly includes a lot of jargon, it may be worth creating these lexicon objects first.