Thank you! A lot of people have mentioned this to us already - we did not think about the LLM use case when getting started with Revideo, but it does make a lot of sense that it can be used to build text-to-video products and fully automate video editing.
As you mentioned, letting LLMs generate high-quality Revideo code is probably not yet possible, but something I believe could make a lot of sense is using LLMs to choose parameters for your video. Video parameters can get as complex as you like in Revideo (any JSON object is accepted), so you could build a very flexible template that lets you define pretty much any video by using a "universal" JSON representation (essentially, this would be a list of elements such as audio files, videos, images, texts, along with attributes describing the timing, position, etc. of the element)
Letting the LLM generate input variables for your template instead of the code would at least allow you to do type checking and ensure that there are no bugs in your video code - however, I still doubt that the resulting video will be of high quality, LLMs are probably not yet smart enough for this.
As you mentioned, letting LLMs generate high-quality Revideo code is probably not yet possible, but something I believe could make a lot of sense is using LLMs to choose parameters for your video. Video parameters can get as complex as you like in Revideo (any JSON object is accepted), so you could build a very flexible template that lets you define pretty much any video by using a "universal" JSON representation (essentially, this would be a list of elements such as audio files, videos, images, texts, along with attributes describing the timing, position, etc. of the element)
Letting the LLM generate input variables for your template instead of the code would at least allow you to do type checking and ensure that there are no bugs in your video code - however, I still doubt that the resulting video will be of high quality, LLMs are probably not yet smart enough for this.