ModelTalker Interactive Demo

Below is an interactive text-to-speech form** that demonstrates ModelTalker with different talkers (some professional). Most demonstration voices are unit selection (uSEL) synthesis made with standard 1600 sentence inventories. However, check out the several Tom voices that illustrate quality differences for inventories of 400, 1600, and 3155 sentences using both uSEL and hybrid DNN (hDNN) technology.

Please type or paste some sample text below (one sentence at a time):


** Demo and samples for illustration and non-commercial use only.