New Training: Integrate Amazon Polly Voiceovers to Your Business Applications with PowerShell
In this 6-video skill, CBT Nuggets trainer Trevor Sullivan leverages Amazon Polly to manage a text-to-speech (TTS) service that generates audio content with the AWS SDK for PowerShell. Watch this new AWS training.
Watch the full course: AWS Cloud Automation
This training includes:
- 6 videos
- 55 minutes of training
You’ll learn these topics in this skill:
- What is Amazon Polly?
- Using Amazon Polly from the AWS Management Console
- Configure PowerShell Development Environment for Amazon Polly
- Exploring the Amazon Polly APIs for PowerShell
- Generate Audio Files with Amazon Polly and PowerShell
- Use SSML Tags to Modify Speech in Amazon Polly
How to Convert Text to Speech in PowerShell with AWS Polly
Amazon's Polly service is a great way to convert text into speech through an automated process. Polly can be used for all sorts of things like enabling access features on websites or apps. Though text files can be converted to audio through Polly's AWS dashboard, it would be convenient to convert text files programmatically instead. This process can be done through various programming languages and command-line environments, but PowerShell is especially suited for this task due to how it manages data differently than other CLIs like Bash.
PowerShell treats data as objects instead of strings. This is perfect for the AWS SDK since most commands typically require some form of a data object to work properly. Polly is no different.
To call Polly through PowerShell, first, make sure you have the AWS Tools for PowerShell cmdlets installed. Once those are installed, use the Get-POLSpeech cmdlet.
The Get-POLSpeech cmdlet includes 11 additional flags:
- LexiconName <String>
- SpeechMarkType <String>
Note that the Text, OutputFormat, and VoiceID flags are required. The others are optional. You can find the VoiceID from the Polly Dashboard within your AWS account.