Amazon Polly is a service that turns text into naturalistic speech, letting you create applications that talk and build new types of speech-enabled solutions. Polly's Text-to-Speech (TTS) service uses advanced deep learning technologies to synthesize natural-sounding human speech. You can build speech-enabled applications that work in many different countries with dozens of lifelike voices across a broad set of languages.

Using Amazon Polly TTS Service, you can:

  • Build a speech-enabled bot
  • Integrate a user interface into your system
  • Use speech-to-text transcription to support your applications.
  • Use the text in your system via long-form and short-form documents, blog posts, emails, and more.

Cloud Architect (AWS & Azure) Masters Program

Become A Globally-recognized Cloud ArchitectExplore Course
Cloud Architect (AWS & Azure) Masters Program

Install Amazon Polly TTS Service

To get started, you can install the Amazon Polly TTS Service by running a series of commands with a bootstrap package, which is necessary to make Polly TTS Service work with Amazon Elastic Compute Cloud (EC2):

aws lambda -m com.amazon.polly.tts -s <service name>

On AWS CodeStar, click "Add a New Service" and select the bootstrap service.

To begin using the Amazon Polly TTS Service, you can provide the service with a textual document of the desired language. You can also provide a sample text to use as input. Still, we recommend providing a sample sentence to avoid potential errors and to ensure that the resulting words and phrases are correct.

If you are only using the text in your system to build your system, you can get started by clicking "View Document" in the Amazon Polly TTS Service web portal and selecting a sample sentence. Click the "Generate Speech" button to receive your text-to-speech output, which you can publish to Amazon Polly Connect in your application. You can also use your application's speech output from Amazon Polly TTS Service.

To generate the text from a word, you can select the word or part of the word you want to translate to speech. The reader will highlight the word or role of the word and specify a list of words and phrases, such as "tears," which should be translated to "tears." You can click the "See Transcript" button to verify your translations at the top of the screen.

Note: You can use the top "Generate Speech" button to see the generated text.

From the Lambda dashboard, you can find the Lambda function. Create a Lambda function named "TTSSpeechService" and select AWS Lambda in the AWS Marketplace.

The Lambda function takes a sample text document (from the Amazon Polly Web API). It renders it into a textual record, which you can publish to Amazon Polly Connect in your application.

Connect to the Lambda function using the Webhook URL to run your TTS service.

  1. Go to the AWS Management Console (aws.amazon.com).
  2. Navigate to your newly created lambda project and choose "Create a new lambda."
  3. Click "Add a New Function."
  4. Click "Lambda Function" and choose the new lambda from the list of available functions.
  5. Select the new lambda from the list of functions and choose "Use webhook as the event source."
  6. On the AWS Webhook side, ensure you have linked the server URL that is available in the example "TTSSpeechService" lambda function.

To test your application, go to "To Alexa," available in the menu bar, and select "Cortana." On your PC, click the microphone icon in the menu bar, type "TTSSpeechService" into the search box, and press ENTER.

Say “TTSSpeechService” to your PC

To test your application with AWS Alexa, go to the Alexa app and enable "TTSSpeechService" in the apps section.

Say "TTSSpeechService" to your Echo

Be sure to stop and restart your service or follow the steps in the sample to find the nearest server and update your service. If you have trouble with your service, you can search for the issue on GitHub.

Master's Program: AWS Cloud Architect

Become an Expert in Amazon Web ServicesEnroll Now
Master's Program: AWS Cloud Architect

Why Would You Want to Use AWS Amazon Polly Text-to-Speech (TTS) Service?

Anyone can use Amazon Polly's built-speech synthesizer for typing text, speech, and human accents. To use the service as a text-to-speech service, you need to use its custom TTS available through the AWS marketplace. It lets you develop your TTS based on structured data. You can also create your text-to-speech synthesizer for Alexa skills.

TTS is often used to make soft synthesized voices of individuals with speech impediments. Because this type of voice (TTS) is usually played back without speech delay, it is helpful for businesses and other environments where the goal is to deliver a message or response in a given amount of time. Amazon Polly's custom TTS service supports MSType.

TTS is often used to make soft synthesized voices of individuals with speech impediments. Because this type of voice (TTS) is usually played back without speech delay, it is helpful for businesses and other environments where the goal is to deliver a message or response in a given amount of time. Amazon Polly's custom TTS service supports MSType. Support for Overlaid Speech: Overlaid speech is an encoding format designed to significantly improve the accuracy of speech synthesized from a set of handwritten letters. Overlaid speech is made available through Amazon Polly's TTS custom service.

Overlaid speech is an encoding format designed to improve the accuracy of speech synthesized from a set of handwritten letters. It is made available through Amazon Polly's TTS custom service. Custom data models: Amazon Polly can read several data types, including binary (base64 encoded) and text. But the custom service (offered through the marketplace) supports several data types and makes them available in one table.

Amazon Polly can read several data types, including binary (base64 encoded) and text. But the custom service (offered through the marketplace) supports several of these data types and makes them available in one table. 

Switching based on the type of data: Amazon Polly supports the "opacity" of speech in a two-tone scenario (one tone in the "alpha" and another style in the "beta" octave) and several other variants. This feature is also available through the custom service. If you use the custom service, you will be able to provide access to only the "alpha" or "beta" octave and disable the "opacity" of the speech.

Become an AWS Wizard with our in-depth Cloud Architect Master’s Program. Enroll now!

Summary 

Polly's TTS is a great feature that's easy to configure and implement. Once you get up and running with Polly, consider how you will use it and talk to your customer service representative to discuss the new service. You can get started by adding a few simple features. 

Amazon Polly's ability to read multiple data types makes it an excellent solution for data-driven conversations. You will be able to interact with customers in more natural ways as a result. And the technology behind Polly makes it easy to do so.

Simplilearn offers comprehensive skills training programs in cloud computing, such as the Cloud Architect Masters Program. This twelve-month program is an online bootcamp composed of eleven courses featuring live virtual classrooms, hands-on labs, and projects. Simplilearn's programs are a great way to advance your cloud computing career.

About the Author

Matthew DavidMatthew David

Matt is a Digital Leader at Accenture. His passion is a combination of solving today's problems to run more efficiently, adjusting focus to take advantage of digital tools to improve tomorrow and move organizations to new ways of working that impact the future.

View More
  • Disclaimer
  • PMP, PMI, PMBOK, CAPM, PgMP, PfMP, ACP, PBA, RMP, SP, and OPM3 are registered marks of the Project Management Institute, Inc.
  • *According to Simplilearn survey conducted and subject to terms & conditions with Ernst & Young LLP (EY) as Process Advisors