Google's DeepMind AI fakes some of the most realistic human voices yet

WaveNet, as the system is called, generates voices by sampling real human speech and directly modeling audio waveforms based on it, as well as its previously generated audio. In Google's tests, both English and Mandarin Chinese listeners found WaveNet more realistic than other types of text-to-speech programs, although it was less convincing than actual human speech. The alternative is parametric text to speech -- building a completely computer-generated voice, using coded rules based on grammar or mouth sounds. Google's system is still based on real voice input.