Ilkay is the creator of the first text-to-speech engine and application for Turkish in 1997 (SpeakTurkish).
We are dedicated to creating learning and self improvement software for people from all walks of life using newest technologies. VocaTalk is our first product and is currently in public beta. We are working on other cool technologies that will eventually become a coherent suite of applications that will change the way you reach and keep up with information.
VocaTalk uses various DSP (Digital Signal Processing) technologies to enhance the speech output. Speech engines usually use 16Khz or 22Khz sampling rate. But VocaTalk's output is always at 44KHz (CD quality). The speech engines normally produce mono output. But VocaTalk's output is always stereo. VocaTalk applies various effects to the sound after resampling up to 44Khz, so the new sound has more details than the original. For example, a 16Khz voice is resampled, turned into stereo, and enhanced by effects that operate on the extra samples which is 4 times the original. Effects like positional audio, echo, voice pitch modulation thus produces a richer and lifelike sound. Audio output from different voice engines can be at different levels caused by the original samples used. VocaTalk automatically adjust volume level to be the same for all voices. VocaTalk also suppresses artifacts that may be produced by signal processing by using digital filtering and floating point precision.
Download
