Automatically Add Audio to Your Website with Amazon Polly

You can now listen to this article
Subscribe
Voiced by Amazon Polly

I suspect you understand that your website is one of the primary tools you use to engage with both prospects and clients. It is how many people find you and starts the process of understanding what you offer. It is also a channel your clients can use to access information, documents, and other tools to help them better manage their insurance program.

Amazon Polly

The expectation of website visitors continues to change. One engagement tool I have added to my website is the ability to automatically create playable audio for every article I publish using the Amazon Web Services (AWS) Polly Service.

WordPress Plugin for Amazon Polly

Amazon Polly is a web service that automatically converts text to audio. Using the Amazon Polly plugin for WordPress, you can provide visitors to your WordPress website with audio recordings of your content. The plugin creates audio files in any of the voices and languages supported by Amazon Polly. Your visitors can stream the audio at their convenience using inline audio players and mobile applications.

You can configure the plugin to do the following:

  1. Automatically create audio recordings for new content upon publication, or choose to produce recordings for individual posts.
  2. Create audio recordings of your archived content.
  3. Use the Amazon Pollycast RSS feed to podcast audio content (more about this service in an upcoming issue).

Requirements

The easiest way to use the service is on a WordPress website. So the requirements are:

  • A site using WordPress
  • An Amazon AWS Account
  • A bit of technical knowledge (but not as much as you would think)

If you don’t have a WordPress website, then your developer might be able to use the Amazon Polly API to program this capability into an existing website. However, that is beyond the scope of this article.

Amazon Polly: How It Works

Once installed, the WordPress plugin automatically sends your text to the AWS web services to process into an audio file.

Amazon Polly converts input text into life-like speech. You call one of the speech synthesis methods, provide the text you wish to synthesize, select one of the available Text-to-Speech (TTS) voices, and specify an audio output format. Amazon Polly then integrates the provided text into a high-quality speech audio stream. See the screenshot.

Input text – Provide the text you want to synthesize, and Amazon Polly returns an audio stream. You can provide the input as plain text or in Speech Synthesis Markup Language (SSML) format. With SSML, you can control various aspects of speech such as pronunciation, volume, pitch, and speech rate.

Available voices – Amazon Polly provides a portfolio of multiple languages and a variety of voices, including a bilingual voice (for both English and Hindi). For most languages, you can select from several different voices, both male and female. You specify the voice ID name when launching the speech synthesis task, and then the service uses this voice to convert the text to speech. Amazon Polly is not a translation service — the synthesized speech is in the language of the text. However, numbers using digits (for example, 53, not fifty-three) are synthesized in the language of the voice.

Output format – Amazon Polly can deliver the synthesized speech in multiple formats. You can select the audio format that suits your needs. For example, you might request the speech in the MP3 or Ogg Vorbis format to consume in web and mobile applications. Or, you might request the PCM output format for AWS IoT devices and telephony solutions.

There are many options available that allow you to customize how the play displays on the page. There is even an option for “Automated breaths.” If enabled, Amazon Polly automatically creates breathing noises at appropriate intervals. Really!

I added Amazon Polly capability to my article a couple of months ago. I set it up myself, without any help. I am a bit more technical than some, but certainly not a programmer. It was easy, and now my site has the added benefit of allowing anyone to listen to my articles.

The cost to use Amazon Polly is $4 per 1,000,000 characters. A few weeks ago, I received my first bill from AWS for $0.13 for two months of use. I could convert every article on my site (and there are a lot) for under $8 total. It is ridiculously inexpensive.

Click here for step by step instructions for installing and using the WordPress Plugin for Amazon.

In a future TechTips, I’ll talk about some of the additional capabilities of the Amazon Polly plugin including translation, podcasts, and Alexa integration.

A side benefit of adding audio capability to your website is that it becomes more accessible and might help prevent a lawsuit against the agency.

What do you think? Is this just a gimmick or something that would enhance the capability of your website.

Please note: I reserve the right to delete comments that are offensive or off-topic.

Leave a Reply

Your email address will not be published. Required fields are marked *

4 thoughts on “Automatically Add Audio to Your Website with Amazon Polly

  1. One massive weakness is you can’t specify voices on the fly. So you couldn’t have two or three voices reading the text and switching on cue like a real conversation. You have to make separate audio, chop it up, splice the parts together then run an SML script to pull in each segment. How tedious. Maybe it will come but it ain’t possible now.