Amazon Polly can be used to convert text in to speech. It is part of the Amazon Web Services (AWS) cloud platform and can be used to create speech-enabled applications. With over 20 languages available in over 40 unique voices, it uses the latest text-to-speech technology to produce lifelike speech which users can customise in order to control areas such as pronunciation, pitch and speed.
More Accessible Applications
The main use of test-to-speech technology is the opportunity to create applications which are more accessible and easier to digest to all. Creating applications which can talk, and talk in a manner which is easily distinguishable to the listener, has clear benefits for the visually impaired.
There are also many occasions when listening is just more convenient and practical, as opposed to holding a text or screen to read from. Many books also now have audio counterparts, and Amazon Polly takes this further, allowing any written text to potentially be converted in to speech.
Advantages of Customisation for the User
This is a text-to speech platform which offers fast response times across multiple languages. As a cloud based system it reduces the need for local resources which can be costly and limit the functionality of the software.
Through AWS and its support of Speech Synthesis Markup Language (SSML) users can customise the software to deliver the flexibility in order to create lifelike speech patterns. Users can adjust the speech rate, pitch and loudness to suit requirements, and also adjust the maximum duration of the speech to fit in to video time frames, particularly useful if the text has been translated from another language prior to conversion to speech. Their customised vocabularies allow users to customise pronunciation of company names for example.
A Cost-effective Solution
Although you will need an Amazon Web Services account before starting, the costing methods make this a cost-effective text-to-speech application with free and premium tier options available.
With no set-up costs involved and a pay as you go pricing model, users can scale up as their application develops and grows. In 2018 Amazon introduced a plug-in for WordPress which is simple to install, giving users the opportunity to easily integrate speech-enabled applications in to their websites.
With a simple to use API the advantages of speech-enabled applications are available through AWS and are quick and straightforward to integrate in to applications. The success and acceptance of any text-to-speech technology is based on how easy it is to use and the lifelike, non-robotic nature of the voice heard by the end user.
Amazon Polly aims to deliver on both fronts, looking to its customisation offering to allow users to create the voice of their choosing in the language of their choice at the right pitch and speed for them.
Maybe you'll be interested in this ebook: