CUTalk is a set of Application Programming Interfaces (API) for Cantonese text-to-speech synthesis. It can efficiently convert Chinese text into Cantonese speech, either to computer audio output or to an audio data file. CUTalk enables system developers to empower their products and services with speech output.

The basic functions and features of CUTalk include:

  • converting text input to speech output
  • switching between male and female voice
  • adjustable speaking rate
  • choice of output format (computer audio output or audio file)

In addition, the software have the following advanced features:

  • multi-thread safe
  • run on Microsoft Windows and Linux platforms
  • different output file formats, e.g., mu-law compressed or raw wave
  • handling most homograph (one word multiple pronunciations) problems in Chinese
  • accept Big5 or GB encoded input text
  • different ways of reading numerals, i.e., digit string or number
  • skipping or reading out punctuation marks
  • spelling out English alphabets

More information can be found from:


Samples Speech Files

努力成為香港、全國及國際公認的第一流研究大學,並使我校建立於雙語及雙文 化傳統的學生教育、學術成果及社會貢獻,保持在卓越水平。

在各個學科領域,全面綜合地進行教學與研究,提供公共服務,致力保存、創造 、應用及傳播知識,以滿足香港、全中國,以至世界各地人民的需要,並為人類 的福祉作出貢獻。

If you have got a licensed version of the CUTalk, there are several additional examples for investigating the capability of the API.


CUTalk is now available for licensing. Click here for the prices. You may first get an evaluation version (with limited capability) to investigate the feasibility of integration with your intended applications. For further details, please contact Ms. Tracy PANG (, Technology Development Team, Office of Research and Knowledge Transfer Services (ORKTS), CUHK.


Prof. Tan Lee
Department of Electronic Engineering, The Chinese University of Hong Kong,
Tel: (852) 39438267
Fax: (852) 26035558