Talking Instead of Typing: First Impressions on Voice Prompting
Recently in Brazil we had the Megabrain meme. If you're not familiar with it, it was a video of Thiago Finch, a famous influencer here, talking with an AI and dictating his prompts. A lot of people, including me, thought it was funny because he looked like Tony Stark talking to Jarvis. He made a reply video saying that dictating is what he uses because it gives more details and more context to the AI. I found that curious, and I started considering testing it myself.
I also saw my friend and CEO at the company I work for, Filipe Nevola, writing documents, replying to messages, and opening GitHub issues just by dictating. So I decided to start prompting by voice in my day-to-day work.
Well, I've been doing this for a few days and, to my surprise, it's very good. Thiago Finch was right. I can generate large prompts with more details and more context, much faster than before. I can ask the AI to adjust and improve things just by talking about what I'm thinking. Even the posts I write, I can do just by talking. The last post and this one were written using dictation.
I'm using this on Cursor, and the voice mode is very good. I'm not a native English speaker, so I have a strong accent when I speak, but even talking slowly, the AI recognizes the text and creates good output.
I don't know if I will keep using this every day, but my first impression is that it's a very useful tool. If you aren't a Cursor user yet, I highly recommend giving voice mode a try. You can sign up through my referral link. Maybe it's not worth it if you work around more people, like in an office, but if you're on home office, maybe it's a good option.
As a final benefit, and not the least important: if you're not a native English speaker, you'll be training your speaking while you work. Win-win.
If you've already tried it, feel free to reach out. I'd like to hear your experience.
See you next time!