logoalt Hacker News

dverlaeckt80 • today at 6:02 PM • 3 replies • view on HN

This is actually quite impressive from an engineer viewpoint. I just have the feeling that the videos quickly become very monotonous and rather boring due to the monotonous AI voices. If somehow you could bring dynamic variation in these videos that would be fantastic.


Replies

jonplackett • today at 7:10 PM

The thing I like about an explainer video is the personality and insight of the person giving it.

Like Marquise Brownlee just has opinions I care about and I watch his videos for this reason.

If a video just explains something I could just read all I’m getting is a layer of obfuscation.

➕ show 3 replies
mrborgen • today at 8:01 PM

Thanks! And I agree. We're getting tons of requests for more nuance in voice selection from our users. You're currently able to say i.e. "Australian English female" in your prompts today, but you should also ideally be able to describe the voice characteristic (i.e. like a funny grandpa, engaged news reporter).

What Gemini 3.8 Flash TTS is doing with generative voice design in this area super interesting.

itomato • today at 7:27 PM

0:04 for the first , 0:02 for the second. I'm personally all done with that.