Our text-to-speech (TTS) system creates human-like voices from written text for the South African market. These synthetic voices can say and read anything in South African languages, on a wide range of devices and platforms, for industry, developers and individuals.
The Voice Computing Research Group within the CSIR studies the way in which speech- and language-related technologies can be created and applied to benefit the people of southern Africa. South Africa is a multilingual country, with eleven official languages, requiring unique text-to-speech solutions to accommodate the diversity of languages. This uniqueness has led to years of research and more recently the development of text-to-speech (TTS) voices for the eleven official South African languages. The TTS voices can be used for impact in real-world applications, such as disseminating information, providing dynamic content, enhancing digital literacy and enabling communication, to name but a few.