Text-to-speech technology enables people who are blind or visually impaired to have more audiobooks available to them. more audiobooks available
It is clear that the goal of technology is to make people's lives easier. In the era of digitalization and the application of Artificial Intelligence and the Internet of Things, the benefit it brings us is expanding to areas previously unthinkable. One of its great achievements is the opportunities it offers us to promote and improve inclusion.
For example, through Custom Neural Voice in Microsoft Azure Cogitive Services it is becoming possible to convert text to voice quickly and with a natural result. This means the creation of many audio books that enable blind and visually impaired people to access more knowledge and acquire new skills. This text-to-speech technology is supported by the Audio Content Creation platform.
Custom Neural Voice
It is a text-to-speech (TTS) functionality that allows creating a customized synthetic voice for applications. It is based on three components: Text Analyzer, Neural Acoustic Model and Neural Vocoder. From there it generates very natural synthetic voices from text. More information about this functionality in this link.
Audio Content Creation
It is a tool that allows you to create audio content for different fields. For example, audio books, video narrations, for bots, etc. It is easy to use and the results are very natural. Audio Content Creation allows you to adjust voices, e.g. speed or pronunciation, and create personalized experiences. An Azure account is required to use it.
