📜 ⬆️ ⬇️

A new version of the mobile application "Reader" for iOS has been released



A bit of background
Two years ago, we released the first version of Reader for iOS (Link to iTunes ). This is a mobile application that reads books and text documents loaded into it using Russian synthesis technology. In fact, it allows you to voice in real time any book (.txt, .doc, .fb2). Books are voiced directly in the mobile device, constant access to the Internet is not needed. During this time, "Reader" installed about 100 thousand users.


New in the application
In the "reader" updated design. There is support for the latest version of iOS. Worked on ergonomics and navigation, taking into account the comments of our users.
Made the ability to install additional votes. So far there are only 4 of them (2 male and 2 female), but in the next update we plan to support seven votes already.
We also added the ability to work with a font - you can choose the font style and change its size.

A small video review of what "Reader" can
')


Future plans
We plan to expand the functionality and improve the usability, taking into account the wishes and comments of our customers in the AppStore.
In the near future, the introduction of the English voice (by the end of 2014), and the support of Kazakh - it will be implemented in 2015.
The “Reader” is now being developed for Android and we plan to post it on Google Play by the end of September. A plug-in application is also being prepared for easy integration of our synthesis into other applications and third-party readers.

About speech synthesis technology
Our speech synthesis technology uses the original hybrid implementation of several well-known technologies: Unit Selection and statistical modeling of speech parameters based on hidden Markov models (HMM). The first of them provides a natural timbre of the sound of the synthesized voice, and the second allows you to give the voice the necessary intonation, semantic and emotional coloring.
In addition to the natural timbre and intonation of the voice, the speech synthesizer is able to understand the meaning of the text depending on the context, ensuring the correct pronunciation in ambiguous situations due to the wide range of vocabulary, abbreviations, abbreviations and much more.

Useful information
We recently did a TTS SDK for Android and iOS - so now our speech synthesis technology can be used in third-party mobile applications. Interesting? Contact voicefabric@speechpro.ru
There is also an opportunity to voice Internet sites and videos with our synthesis, for this we launched a separate project: VoiceFabric.ru

PS Completed the article with a video review.

Source: https://habr.com/ru/post/233477/


All Articles