Capit is an iOS app built using GPT4-Vision that can automatically generate intriguing social media captions for both images & video. Just choose an image, define your tone, decide if you want hashtags & emoji and then you get 5 creative caption ideas!
Hello Hunters! 👋🏻 I am Jason Clardy, the indie-on-the-weekends developer building iOS apps for my side project company, Swift Fox Software (https://swiftfox.co). I built Capit in a few weeks during the early mornings and over a few weekends, though I'm not a social media guru - I find it pretty fun to play around with just to see what GPT comes up with for random photos I've taken.
The Problem 🤔
My wife runs a small retail storefront, and one of our biggest traffic drivers is our instagram page. Unfortunately, my wife despises social media, and so making multiple posts per week becomes quite a chore, but it is extremely beneficial to the business. The main problem is just constantly writing captions for every post, when a lot of your content is in similar categories. So the problem is - how can we automate our social content creation pipeline as much as possible and inspire more creativity in our copy?
The Solution ✨
GPT4-Vision! When I saw this announced a few weeks ago I knew I had to try and build this app. There are other caption assistant apps on the app store currently, but they all require you to type out a description of exactly what you want. Capit streamlines this process by just taking your image or video directly, and figuring out the context on its own.
Tech Stack 💾
GPT4-Vision - Image understanding
Firebase Firestore - History storage
Firebase Cloud Functions - API
RevenueCat - Subscription management
DeskFrame