sure. the video conversion is running on AWS Fargate, with bits and pieces running on AWS Lambda. The speech synthesis is either Amazon Polly (neural voices) or Google Cloud Text to Speech (Wavenet).
Under the hood, the conversion system is using Chrome headless to generate slides, render markdown and provide syntax highlighting. Most of the video and audio processing is with FFMpeg and SOX.
In the meantime, could you write a bit what different pieces of technology/services you're using to build all this?