Speech-to-text is amazing

Is this blog entry about speech-to-text? Yes. I am using speech-to-text to write it. This is a PSA about using speech-to-text because I am blown away by its current state. As someone who types slowly—about 60 to 70 words per minute—speech-to-text is truly game‑changing. Now it’s something you can download on your computer. I’m using OpenWhispr’s software with local models, which is slower on my ThinkPad because it lacks computing power. On a MacBook or a powerful computer with a decent GPU, you can get extremely fast speech‑to‑text. Their cloud version is also incredibly quick.

This entire blog entry is just to tell you to use speech‑to‑text because it is way faster. The technology has improved drastically over the years. I originally avoided speech‑to‑text because it was inaccurate, but now it works like autocorrect, a bit of Grammarly, and speech recognition all at once, and it does so super fast and efficiently. I’ll be using it for school and all my assignments. It makes everything better, especially for me, who drinks coffee and then has thoughts everywhere. Writing used to kill a lot of time, but now I can blast information to my computer as I think of ideas.

I also want to explore editorializing speech‑to‑text. I don’t have a plan for refining it yet, but that’s something to look into after creating this PSA. I literally completed a 1,200‑word assignment in about 20 minutes using speech‑to‑text, and it turned out well. You don’t even need to edit much if you learn to use it well.

Another great use is with artificial intelligence. I use Agentic AI, and combining it with speech‑to‑text is truly game‑changing. I no longer need to touch the code base. Coding is in a weird place right now, but you should use speech‑to‑text, guys. It’s amazing.

(this is unedited speech-to-text)