Hi,
I want to build a text-to-video maker similar to Fliki.ai (powered by OpenAI GPT-3 & DALL-E). I have already built an AI writer sometime back using Bubble and OpenAI GPT-3!
What is the best way to build a text-to-video maker in Bubble? The user should be able to download the file in the end.
Basically, think of it like a slideshow of Group elements wherein each Group may contain the text and image/video. Probably, this screenshot can give you a better understanding of what I am looking for! The image and video may be sourced from the stock image providers such as Pixabay, Freepik, etc.
Think of each scene as a combination of text and image OR text and video (of course, audio needs to be added, that is another big issue to ponder over!)
There are already tons of text-to-video AI tools out there such as Steve.ai, RunwayML, Pictory, Fliki, etc. And almost all of them use the same logic except that the interface is different. I would like to create a better version of Fliki!
I tried Zeroqode’s Group to Image Converter plugin. But, I can’t find any such thing for Group to Audio/Video Converter.
Highly appreciate your help…
Thanks,
Shashank