Speect is a multilingual text-to-speech (TTS) system. It offers a full TTS system (text analysis which decodes the text, and speech synthesis, which encodes the speech) with various API’s, as well as an environment for research and development of TTS systems and voices.
Speect is written in the C language, with a strict conformance to the ISO/IEC 9899:1990 standard, thereby allowing for maximum portability to different computing platforms. Platform specific system calls are abstracted to allow ports to new platforms.
Speect also includes Python bindings for general customization and quick implementation of new ideas, and uses a plug-in mechanism for extensions. It is still under constant and active development, but can already be used for creating TTS voices, and doing research.
Speect is being developed by the Human Language Technologies group at the Meraka Institute, CSIR, South Africa. We use it in our projects (see http://www.meraka.org.za/lwazi/) as a TTS server for multilingual text-to-speech synthesis.