Good tips, especially the point about narrowing the scope. At https://Lemonfox.ai we started with a LLM, image and speech-to-text API. Now we are only focusing on the speech-to-text API as the other areas are already very crowded and there's a lack of innovation in the speech-to-text space.
cootsnuck|1 year ago
I'm legitimately wondering how your hosted Whisper API for $0.17/hr is supposed to compete with groq's exact same API that costs $0.03/hr.
You may be about to find out how crowded all of the AI infra spaces are.
I strongly recommend narrowing your scope far beyond modality. If you've been working with this tech and getting familiar with it then you already have valuable expertise. Pivot now or panic later. If you want to stay in the speech space find what markets are being underserved with speech AI related solutions. Are there pain points there that can be solved by a STT API? If so, build those solutions. You can't compete at the infra layer and I'm not sure why you would want to try if you don't already have something unique about your offering beyond hosting open source models. It's never good if your competition is potentially just a single developer in a company standing up your entire service internally in a week.
If you are determined to stay in the AI infra space then you'll need to be tackling a hard problem that companies want solved. Maybe take a look at fine-tuning models. Hard problem and maybe there's a hunger for it. (It's a risky one to tackle too though since it's very possible general/foundational models will maintain a grip on "good enough".)
anonylizard|1 year ago