Since the release of GPT’s proper voice mode, where it sighs and such, I’ve been using voice agents for ideating and learning more. Recently, Anthropic updated Claude’s own voice mode and I think it’s powered by ElevenLabs their voice models (just an assumption based on how it sounds) and I have to say: I’m impressed.

The voice sounds very natural yet it answers concise enough for me to just have a naturally flowing conversation with it. Where Gemini constantly says “I’m not a doctor” or ends the message in “What do you think?” this agent just answers. Of course, when it’s gets political or medical it refuses but in a natural way without feeling like it has to say it.

Often, in the car, I call with agents to learn new things while I’m on the road or just kill the time. In the beginning, it felt very strange (because it is) but nowadays it’s something I do for hours and just enjoy it.

No, it doesn’t feel like talking to a human nor does it feel like a friend. But it makes my commute a moment to learn, to think, to reflect and to become better.

And no, it’s not the only thing I do in the car. I still listen to podcasts, I still listen to music, I still sometimes listen to nothing and just think. It’s just something else you can do while driving, which isn’t that cognitively intense yet fun to do.