Show HN: FaceTime-style calls with an AI Companion (Live2D and long-term memory)
31 points by summerlee9611
by augusteo
2 subcomments
Building on zemo's point about parasocial relationships: traditional parasocial interaction involves a performer who doesn't know you exist. Here the AI does respond to you specifically, which changes the dynamic.
Is it still parasocial if the other party is responsive but not conscious? Or is this something new that we don't have good language for yet?
by nitroedge
0 subcomment
For better lip sync you could try using rhubarb to extract from the mp3.
What is your backend speech processor so you can get the real-time streaming response?
Rhubarb would add a bit of latency for sure.
by october8140
1 subcomments
This is disturbing.
by dummydummy1234
0 subcomment
What are you using for tts/stt/models?
by singular_atomic
0 subcomment
Where’s the asteroid at
by sghimire2022
0 subcomment
This is cool.
by dfajgljsldkjag
1 subcomments
It creates a conflict to build a system that is both a private friend and a public performer. You cannot maximize intimacy and fame at the same time.
Hacker News