[collinvandyck76]

Thank you for sharing. I'm looking forward to getting voice mode, but after doing some searching I saw that it still needed the user to hit the "send" button after they are done talking. Did I misread, or was your experience that it would reply to you after you finished talking without the need to press anything?

[tkgally]

When you’re done talking, you tap anywhere on the screen to indicate that you’re finished talking, and Claude replies a second or two later. If you are silent for several seconds, it goes ahead and replies without waiting for you to tap. When Claude is talking you can tap on the screen to interrupt; that is actually quite useful, as it can be a bit long-winded.

It’s not quite as natural a back-and-forth as with ChatGPT’s or Gemini’s voice mode on mobile, but maybe that’s for the best.

I tried a test later in which I gave it a research paper—Sakana AI’s latest—and asked it to explain it to me. When it used a term I didn’t understand, I just tapped on the screen and asked for an explanation. That worked quite well.

[collinvandyck76]

Thanks a lot. This sounds great for my envisioned use case which is having conversations while on a road trip to research ideas that pop into my head. Not having to tap the screen makes it much safer.

[collinvandyck76]

I finally got access to it -- much better experience than I had expected. I really like being able to choose the voice/cadence. I wasn't able to get it to auto-send after a few seconds, but that might have been due to being in a noisy environment.