The Emic Text-to-Speech Module is a fully-integrated solution that converts digital text into a high-quality English-speaking voice using concatenative synthesis. The module provides a simple interface to a PC, BASIC Stamp, Javelin Stamp, Microchip PIC, or other processor. Voice speed, volume, pitch, and phonetic control can all be adjusted by the user.
Parallax, Inc. was the exclusive manufacturer of the Emic Text-to-Speech module. It has been discontinued as of October 30, 2009.
For an enhanced speech synthesis solution, see our Emic 2 Text-to-Speech Module.
This paper describes our original prototype based on a Handspring Visor Springboard module which is no longer in development.
The speech technology industry is trending towards software-based speech synthesis and recognition solutions, which currently require high-powered processors and large amounts of memory running on expensive devices. There are no readily available, low-cost TTS solutions for use in mobile or portable environments that are generalized (requiring only the necessary computational power and functionality) and are user programmable (allowing for an infinite number of applications and uses). This paper introduces Emic, a modular hardware platform intended for use in the design of speech-enabled products.
Published by the Applied Voice Input/Output Society (AVIOS) at the AVIOS Speech Developers Conference 2003, San Jose, California, March 31-April 3, 2003.
These audio samples were recorded directly from the analog output (AOUT) of the Emic module into a PC.