Google & Amazon Text-To-Speech Simulators
Both Google and Amazon provide text-to-speech simulators that allow developers to test
applications and SSML text on these platforms.
Accessing the TTS simulators require setting up accounts with Google Cloud and Amazon Web
Services (AWS), navigating through pages of documentation, and in the case of Amazon Polly,
configuring scripts on a server.
Unless you plan to develop Text-To-Speech applications, we recommend using the tools listed
below, as these are cloud-based, make use of Google TTS and Amazon Polly APIs and allow you
to easily test your SSML files and convert your text into high-quality audio narrations using the
consoles’ features and capabilities without requiring technical skills, editing code, installing
scripts, etc.
WaveNet Vocalizer
Create high-quality Google WaveNet audio narrations from imported SSML files. Pro, Language
& Upgrade options to create files of any size, markup text, translate text into other languages,
add sub-user accounts, etc.
http://positiveaudios.com/tools/wavenet
Script Vocalizer
Create high-quality Amazon Polly audio narrations from imported SSML files. Upgrade options
to create files of any size, markup text, translate text into other languages, add sub-user
accounts, etc.
http://positiveaudios.com/tools/scriptvocalizer
© PositiveAudios.com 1
Google TTS Simulator
Google provides a basic text-to-speech conversion tool here:
https://cloud.google.com/text-to-speech
© PositiveAudios.com 2
Google’s Actions Console includes a TTS simulator that you can use to test SSML elements.
To access Google’s Text-To-Speech Simulator, you will need to do the following:
• Create a Google Developers account (https://developers.google.com)
• Go to https://console.actions.google.com
• Create a new project.
• Go to Test > Simulator.
• You can find the TTS simulator in the console under Simulator > Audio.
• Type your text and SSML in the simulator and click Update and Listen to hear the TTS
output.
Amazon TTS Console
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 synthesizes the provided
text into a high-quality speech audio stream.
To access Amazon’s Text-To-Speech Console, you will need to do the following:
• Sign up for AWS (Amazon Web Services).
• Create an IAM user (Identity and Access Management).
© PositiveAudios.com 3
• Install, Set Up & Access the AWS Command Line Interface (CLI)
Full information about the above process can be found here:
https://docs.aws.amazon.com/polly/latest/dg/getting-started.html
Additional information:
AWS Identity and Access Management (IAM)
https://aws.amazon.com/iam
Getting Started
https://docs.aws.amazon.com/IAM/latest/UserGuide/getting-started.html
IAM User Guide
https://docs.aws.amazon.com/IAM/latest/UserGuide
© PositiveAudios.com 4