A few days ago, I asked this community, "What video do you guys need?" And a lot of you said my process of how I build AI voice agents. So in my most recent video titled "How to Build an AI Receptionist for Med Spas," I show just that. I show you exactly the system and structure of my AI voice agents that I use in order to build more reliable, accurate, and production-ready voice agents. I hope you find it useful. If you have questions about the system, or if you have questions about the specific Med Spa nature of the receptionist, please let me know. Thanks!

I'm knee-deep in planning the next few pieces of content and honestly, I'm tired of guessing what will be valuable for my audience. Everyone's throwing around the same recycled voice AI videos. So here's what I want to know - where are you right now? Are you still figuring out if this AI thing is legit, or are you already building for companies but failing in production? And what's the one thing that would actually move the needle for you? Not some theoretical framework - the specific problem that's keeping you from the next level. Most requested topic gets made first. But I need details, not generic requests. The stuff that actually works doesn't sound pretty in a title.

Hello Everyone, im working on a project create Arabic voice agent, im running it locally on a 16gb GPU using vscode and langchain. im struggling to find a good TTS and STT model that is fast and accurate enough. currently i have fine-tuned qwen8b 4bit on my dataset using chromaDB. any suggestions?