Amazon Polly - Developer Guide

1 Amazon PollyDeveloper GuideAmazon Polly Developer GuideAmazon Polly : Developer GuideCopyright 2019 Amazon Web Services, Inc. and/or its affiliates. All rights 's trademarks and trade dress may not be used in connection with any product or service that is not Amazon 's, in any mannerthat is likely to cause confusion among customers, or in any manner that disparages or discredits Amazon . All other trademarks notowned by Amazon are the property of their respective owners, who may or may not be affiliated with, connected to, or sponsored Polly Developer GuideTable of ContentsWhat Is Amazon Polly ? .. 1 Are You a First-time User of Amazon Polly ?

2 1 How It Works .. 3 What's Next? .. 3 Voices in Amazon Polly .. 3 Available Voices .. 3 Listening to the Voices .. 6 Voice Speed .. 7 Common Questions.. 7 General Questions.. 8 Content Rendering .. 8 Data Security and Confidentiality .. 9 Getting Started .. 10 Step 1: Set Up an Account & User .. 10 Step : Sign up for AWS .. 10 Step : Create an IAM User .. 11 Next Step .. 11 Step 2: Getting Started Using the Console .. 11 Exercise 1: Synthesizing Speech Quick Start (Console) .. 12 Exercise 2: Synthesizing Speech (Plain Text Input) .. 12 Next Step.

3 13 Step 3: Getting Started Using the AWS CLI .. 13 Step : Set Up the AWS CLI .. 13 Step : Getting Started Exercise .. 14 What's Next? .. 16 Set Up Python and Test an Example .. 16 Voices in Amazon Polly .. 18 Available Voices .. 3 Bilingual Voices .. 19 Listening to Voices .. 6 Voice Speed .. 7 Changing Your Voice Speed .. 21 Languages Supported by Amazon Polly .. 22 Speech Marks.. 24 Speech Mark Types .. 24 Visemes and Amazon Polly .. 24 Using Speech Marks.. 25 Requesting Speech Marks .. 25 Speech Mark Output.. 26 Speech Mark Examples.

4 27 Requesting Speech Marks Using the Amazon Polly Console .. 28 Using SSML .. 30 Using SSML in the Console .. 30 Using SSML in the AWS CLI .. 31 Using SSML With the Synthesize-Speech Command .. 31 Synthesizing an SSML-enhanced Document .. 32 Using SSML for Common Amazon Polly Tasks .. 33 SSML Tags Supported by Amazon Polly .. 35 Supported SSML Tags .. 35 Managing Lexicons .. 115 Applying Multiple Lexicons .. 115 Managing Lexicons Using the Console .. 116 Uploading Lexicons Using the Console .. 116 Applying Lexicons Using the Console (Synthesize Speech) .. 117iiiAmazon Polly Developer GuideFiltering the Lexicon List Using the Console.

5 118 Downloading Lexicons Using the Console .. 118 Deleting a Lexicon Using the Console .. 119 Managing Lexicons Using the AWS CLI .. 119 PutLexicon .. 119 GetLexicon .. 123 ListLexicons .. 124 DeleteLexicon .. 125 Creating Long Audio Files .. 126 Setting Up the IAM Policy for Asynchronous Synthesis .. 126 Creating Long Audio Files (Console) .. 127 Creating Long Audio Files (CLI) .. 128 Code and Application Examples.. 131 Sample Code.. 131 Java Samples .. 131 Python Samples .. 137 Example Applications.. 142 Python Example .. 142 Java Example .. 152iOS Example.

6 156 Android Example .. 158 WordPress Plugin .. 160 Setting Up the Plugin .. 160 Create a Permissions Policy .. 160 Create an IAM User for the Plugin .. 161 Install and Configure the Plugin .. 162 Customizing WordPress .. 162 Storing the Audio Files.. 164 Limits.. 167 Supported Regions .. 167 Throttling .. 167 Pronunciation Lexicons .. 167 SynthesizeSpeech API Operation .. 168 SpeechSynthesisTask API Operations .. 168 Speech Synthesis Markup Language (SSML) .. 168 Logging Amazon Polly API Calls with AWS CloudTrail .. 169 Amazon Polly Information in CloudTrail.

7 169 Example: Amazon Polly Log File Entries .. 170 CloudWatch Integration .. 172 Getting CloudWatch Metrics (Console) .. 172 Getting CloudWatch Metrics (CLI) .. 172 Amazon Polly Metrics .. 173 Dimensions for Amazon Polly Metrics .. 174 API Reference .. 175 Actions .. 175 DeleteLexicon .. 176 DescribeVoices .. 178 GetLexicon .. 181 GetSpeechSynthesisTask .. 183 ListLexicons .. 185 ListSpeechSynthesisTasks .. 187 PutLexicon .. 189 StartSpeechSynthesisTask .. 191 SynthesizeSpeech .. 196 Data Types .. 200 Lexicon .. 201 LexiconAttributes .. 202ivAmazon Polly Developer GuideLexiconDescription.

8 204 SynthesisTask .. 205 Voice .. 208 Authentication and Access Control .. 210 Authentication.. 210 Access Control .. 211 Overview of Managing Access .. 211 Amazon Polly Resources and Operations .. 212 Understanding Resource Ownership .. 212 Managing Access to Resources .. 212 Specifying Policy Elements: Actions, Effects, and Principals .. 213 Specifying Conditions in a Policy .. 214 Using Identity-Based Policies (IAM Policies) .. 214 Permissions Required to Use the Amazon Polly Console .. 215 AWS Managed (Predefined) Policies for Amazon Polly .. 216 Customer Managed Policy Examples.

9 216 Amazon Polly API Permissions Reference .. 218 Document History .. 220 AWS Glossary .. 221vAmazon Polly Developer GuideAre You a First-time User of Amazon Polly ?What Is Amazon Polly ? Amazon Polly is a cloud service that converts text into lifelike speech. You can use Amazon Polly todevelop applications that increase engagement and accessibility. Amazon Polly supports multiplelanguages and includes a variety of lifelike voices, so you can build speech-enabled applications thatwork in multiple locations and use the ideal voice for your customers. With Amazon Polly , you onlypay for the text you synthesize.

10 You can also cache and replay Amazon Polly s generated speech at noadditional use cases for Amazon Polly include, but are not limited to, mobile applications such asnewsreaders, games, eLearning platforms, accessibility applications for visually impaired people, and therapidly growing segment of Internet of Things (IoT). Amazon Polly is certified for use with regulated workloads for HIPAA (the Health Insurance Portabilityand Accountability Act of 1996) and Polly is not certified for use with Payment Card Industry Data Security Standard (PCI DSS) of the benefits of using Amazon Polly include: High quality Amazon Polly uses best-in-class Text-to-Speech (TTS) technology to synthesize naturalspeech with high pronunciation accuracy (including abbreviations, acronym expansions, date/timeinterpretations, and homograph disambiguation).