Sinsy

Sinsy: Singing Text-to-Speech Software

Open-source text-to-speech synthesis with a singing voice function, allowing users to synthesize singing voices from normal text input.

What is Sinsy?

Sinsy is an open-source software application for text-to-speech synthesis with a singing voice function. It was developed jointly by the Nagoya Institute of Technology and the Yamaha Corporation. Sinsy allows users to input normal text and synthesize singing voices that follow the pitch contours and rhythm indicated by the text and markup.

Some key features of Sinsy include:

• Synthesizes singing voices from normal text input using its own singing vocal database
• Allows users to control singing pitch and note durations using markup in the text
• Includes libraries of female Japanese and English singing voices
• Voices can be tuned and configured by advanced users
• Free and open-source software licensed under GPL
• Cross-platform application that runs on Windows, Mac OS X and Linux

Sinsy is targeted at researchers, educators, and hobbyists who want to experiment with computer-generated singing voices. It can be used for creative projects involving synthesized singing, as well as research into speech synthesis and singing voices. The open-source nature of Sinsy also allows for advanced customization and extension of its capabilities.

Sinsy Features

Official Links