19th April 2021

ISSAI scientists have developed Kazakh Text-To-Speech project

Computer voice is now able to read the Kazakh text. This was made possible thanks to the project developed by our ISSAI scientists. They have developed a Kazakh language speech synthesis project, or in other words the Kazakh text-to-speech conversion. Text-to-speech conversion is the artificial production of human speech which allows a computer to read any text in a voice that is as close to natural as possible.

“In Kazakhstan this technology can be used for people with special needs, virtual assistants, and the public services where text-to-speech conversion is necessary. This technology is an essential component in many applications such as interactive smart assistant systems, navigation systems, announcement systems where computer voice-over of the Kazakh text is required The technology can also be useful for visually impaired people, it will allow to establish human-robot interaction by converting Kazakh text into audio”, – says ISSAI postdoctoral scholar Yerbolat Khasanov, – “One of the main goals of our project was to develop the use of the Kazakh language in the digital sphere. Before, we did not meet such ready-made Kazakh speech synthesis projects”.

Scientists have created two versions of the computer voice – male and female which they named Iseke and Raya.

Demo version of the kazakh text-to-speech technology can be tested via the link: Via the link scientists also share the github repository containing pre-trained models and code so that any organizations or individuals can develop their own projects based on our model of the Kazakh speech synthesis technology.

Watch the video about Qorqyt Ata narrated by the male synthetic voice Iseke
Video of the Dina Nurpeisova story narrated by the female synthetic voice called Raya.