Even now, the concept feels solid; all you have to do is speak and slideshow riffs off with you. It is really easy to make terrible slideshows - those are the ones you sit through, looking at the clock while some reads off the slides.
The motivation behind this project was reducing people's dependence on slides when presenting, while providing an engaging visual aid. We get into bad habits with a pre-prepared slide deck: We're less dynamic, more wooden and are oh so tempted to glimpse at the slides. We also have a tendency to put too much information on a slide.
All of these bad habits are prevented with SpeakEasy. You can't rely on it as a memory crutch because it's different every time. It encourages you to speak freely while still emphasizing your points (visually and with bold headers).
We created a pipeline that passes raw audio to the Google Cloud Speech-to-text API, producing plaintext. We then take that text data and apply various natural language processing techniques (including IBM Watson) to generate semantic analysis, from which we can extract key information to format our slides.
Knowing for instance that subject of a sentence can provide a header and the bullet points beneath are the verb-noun pairs corresponding to that subject. We also do a level of emotive analysis for creating color choices for text.
From this we create an internal AST which contains the object types which are then converted into enhanced markdown that can take React Components known as MDX data.
We then hot-reload these files into Gatsby (a React based framework).
If you want to know more, we vlogged the whole hackathon.
mdx-themes, is an easy to use tool.