Qi is a meditation experience which invites listeners to place themselves in absurd scenarios. Existing guided meditation apps tend to focus on a small set of narrow calming experiences ('midnight laundromat,' 'waves on the seashore,' so on) - but why not while hiding from dinosaurs or preparing to ride into battle? Seems even more important to be calm then! Early listener feedback has been that the absurd scenarios are actually more engaging and hold their attention much better.
There is a lot of push to use AI to refine existing workflows or clone existing apps (but with talking to an LLM). That's fine and well, and I think this app shows that we can get 'almost' to a meditation app purely with current AI tech - and multiple meditation apps were valued over $2B over the last couple years, so there's some economic value in doing so. What's _more_ interesting to me, is what AI unlocks that's new: maybe fully personalized experiences, maybe pushing down artistic avenues that are only appreciated by a small niche.
The scripts are generated by a mix of GPT-3.5 and GPT-4. I personally think GPT-4 was significantly easier to work with and that the scripts were better, justifying the additional cost/latency. (Can you tell which of the scripts are generated by 4?). GPT-4 generated much of the Next.js code and helped turn my IPython notebook into a reproducible script as well.
The images were generated by Stable Diffusion v1.5. The audio is synthesized with SpeechT5. Midjourney and ElevenLabs would likely have created higher quality results but I have a GPU just sitting idle :) I also tried to generate background audio via Riffusion but had fairly poor results, would love to improve here.
Very fun project - would love to hear your feedback!
