Demonstrations on customized text to speech synthesis technology (Mandarin)

We provide one-stop fully customized professional text to speech synthesis service, including speech synthesis database design, speech synthesis corpus recording, syllable and phoneme segmentation, and rhythm hierarchy labelling.

Our text to speech synthesis technology has achieved higher speech quality by ensuring better speech clarity, smoothness, stability, and naturalness. Only requiring 1MB Ram and 2MB hard drive resources, our technique is computationally less expensive than other existing systems (usually demanding on 4GB of computing resources), which makes it extremely suitable for mobile applications and smart TV systems.

A demonstrative online text to speech system is presented below:

Huiting News