#295 · how to structure a guarantee with zero data

youtube ↗AI & Automation

How do you achieve high‑quality audio processing with cheap earbuds, and what AI editing workflow do you use?

The trick is to use inexpensive wired earbuds (the $199 Apple earbuds work fine) and place the microphone right next to your mouth. Run the signal through a simple equalizer, noise‑reduction, and a loudness filter, then add an AI filter. I use a platform called Oonic (AUphonic) to handle the AI processing. This setup gives you studio‑quality audio anywhere you travel, even with a $70‑CAD mic, as long as the distance to your mouth stays consistent.

audioearbudsai

Related answers

youtube ↗Other

What microphone do you use?

I use the Samsung Q2U, which costs about $75 CAD on Amazon.ca (roughly $45‑$50 USD). It's the cheapest decent mic around, and with good settings it works very well. I also run my audio through a post‑processing library called Oonic, which I've been using for about a year after a podcaster recommended it.

micequipment
youtube ↗AI & Automation

How do I balance speed with quality for AI automation?

Speed and quality aren't a trade-off; you generally get both. Only in extreme low-latency cases (like real-time voice agents) might you sacrifice quality for speed, using cheap, fast models. For most use cases, the real trade-off is speed and quality versus cost.

speedqualityai
youtube ↗Other

Could you share your audio and mic setup and equipment? Also, are you open to having your voice cloned using 11 Labs for our agents? Feel free to clone me—just let me know when you do.

I'll take the Grimes approach—here’s all of my data, feel free to clone the hell out of me; I have more than enough minutes of me speaking candidly online, so you only need a few seconds. I definitely don’t want to end up operating a phone sex hotline in the future. I feel like I’m going to be getting one of these audio mic setups every day. My setup is a Samsung Q2U microphone hooked up to an Elgato boom arm. I use a service called Aonic to clean up the audio afterward; I could do it myself, but I just prefer the easier option. That’s basically it.

audiomicsetup