I created a fully automated youtube channel that posts new videos everyday, using mostly free and open source AI tools. Here's the link to the full blog post, but here's a TLDR
With a bunch of free/open source AI tools (coqui tts, local LLMs), and a few python scripts written with the help of gpt4, I created a fully automated youtube channel that posts youtube shorts everyday.
I got a whopping 52 subscribers after 6 months of wasting electricity. Besides that, technically, this was a profitable little "thing".
In the end, I loved the process of creating the channel, but I hated the videos I made.
Large Language Models (LLMs) has been amazing for me for being code monkeys that helped me write code. For other written purposes, not so much. Its writing are generic, bland and “soulless”, as they say. More than ever now, I’m allergic to generic written shit (which seems like what most of search results and articles are these days)
Maybe this can turn into a SaaS of some sort in the future that create videos on any topics you want.
Cool project, and I think your conclusion is the most important takeaway: the content ends up generic and soulless.
I work in the YouTube creator tools space and this is something I see constantly — people assume AI can replace the creative process entirely, but what actually works is AI handling the tedious parts (SEO research, metadata, scheduling) while the human brings the perspective and personality. 52 subs in 6 months is actually a pretty honest result for fully automated content.
The real opportunity with AI + YouTube isn't automating content creation — it's automating the strategy and optimization around content that a real person creates. That's where the leverage is without sacrificing authenticity.