Hello, I am the sole developer, designer and founder of the project.<p>We are a two-person company that has bootstrapped the project so far.<p>I hope you like it. Do not hesitate to ask any questions.<p>Some technical nuggets:<p>- We spin up and down a K8s cluster based on load<p>- We use Tacotron and WaveGlow<p>- We use a "tweaked" version of Pix2Pix<p>- We use forced-aligners<p>- We have a speech-to-text DL model<p>- We have around ~30 discrete parts including microservices and cloud functions in an event-driven architecture<p>In broad terms, we manually select news from RSS feeds and then an automated system takes the text out from the news or blog post and generates a video.