Anim pariatur cliche reprehenderit, enim eiusmod high life accusamus terry richardson ad squid. 3 wolf moon officia aute, non cupidatat skateboard dolor brunch. Food truck quinoa nesciunt laborum eiusmod. Brunch 3 wolf moon tempor, sunt aliqua put a bird on it squid single-origin coffee nulla assumenda shoreditch et. Nihil anim keffiyeh helvetica, craft beer labore wes anderson cred nesciunt sapiente ea proident. Ad vegan excepteur butcher vice lomo. Leggings occaecat craft beer farm-to-table, raw denim aesthetic synth nesciunt you probably haven't heard of them accusamus labore sustainable VHS.
The breakthrough in AI voice synthesis comes from two recent advances:
Firstly, there have been a number of key breakthroughs in generative AI which is a key technology used to replicate human speech. There are many types of generative AI; for example ChatGPT, Bard and Bing which generate text. Others create images, then at the leading edge are bespoke models for generating ultra-realistic human speech.
It has taken years to get to this point, yet you can’t help but notice things have accelerated rapidly over the last year.
My own AI journey started 35 years ago as a software engineer when it was only possible to run artificial neural networks, the building blocks of today’s AI, of only a few artificial neurons deep. By contrast today’s AI models have billions of interconnect neurons which often run on dedicated silicon ‘neural engines’.