Free text speech synthesis

High quality text to speech based on real human voices.

Supports mobile OS

Supports iOS/Android/built-in Linux.

Emotion expression is supported

Speakers with emotion expression is now available with micro SDK.

Input Support

Input supports both a mixture of kanji and kana Japanese text and middle notation. (AI special standard, JEITA TT-6004 standard)

General purpose PC SDK
unified with API

By unifying the AITalk5 SDK and API it made possible equivilant functions.

※excluding one part

Low volume dictionary with
separated Japanese analysis

The base unit(Koe no Shokunin in the PC) will conduct a large capacity and highly accurate Japanese analyzing. Then the extention unit (micro SDK) will use a dictionary without Japanese which allows high quality synthesis. with low volume memory and disk.

Phrase dictionary ・Symbol pause
ctionary fuctions

Now able to load the phrase dictionary and symbol pause dictionary made by Koe no Shokunin.

User dictionary function

The user dictionary function registers and saves names of people and places that are read in special ways.

Loading multiple user dictionaries

Can now apply user dictionaries at the same time.

Ruby function

You may now set the way of reading using the ruby function when same kanji characters have a different way of reading.

Bookmark function

You can place a bookmark in any place in the document. You can find information about the bookmark in the callback function.

Voice effect tag function

Specifying various types of parameter values and adding bookmarks is now possible within Japanese texts.

Voice file inserting function

due to the control tag you can insert wav files inside the inserted text

Porting

Porting available for various OS