Hacker News Reader

As weird as it sounds I had this exact thought.

I signed my parents up for Storyworth, which emails them once a week writing prompts about their life.

I'm still weighing the ethical implications of using the entire dataset 20 years from now to generate a facsimile.

Partly I just feel sad about the future, forever chasing digital ghosts of our past loved ones...

That would be a pretty awesome installation at Universal Studios.

But I guess making it not say offensive things might be a problem… or not, depending on the character.

the current workflow I've seen use is midjourney for the portrait creation, elevenlabs to do the voice and D-ID to animate the picture to the voice. Apparently the entire process can take under 15mins.