The idea started as a pretty simple question: text chatbots are everywhere, but they rarely feel present. I wanted something closer to a call, where the character actually reacts in real time (voice, timing, expressions), not just “type, wait, reply”.
Beni is basically:
A Live2D avatar that animates during the call (expressions + motion driven by the conversation)
Real-time voice conversation (streaming response, not “wait 10 seconds then speak”)
Long-term memory so the character can keep context across sessions
The hardest part wasn’t generating text, it was making the whole loop feel synchronized: mic input, model response, TTS audio, and Live2D animation all need to line up or it feels broken immediately. I ended up spending more time on state management, latency and buffering than on prompts.
Some implementation details (happy to share more if anyone’s curious):
Browser-based real-time calling, with audio streaming and client-side playback control
Live2D rendering on the front end, with animation hooks tied to speech / state
A memory layer that stores lightweight user facts/preferences and conversation summaries to keep continuity
Current limitation: sign-in is required today (to persist memory and prevent abuse). I’m adding a guest mode soon for faster try-out and working on mobile view now.
What I’d love feedback on:
Does the “real-time call” loop feel responsive enough, or still too laggy?
Any ideas for better lip sync / expression timing on 2D/3D avatars in the browser?
Thanks, and I’ll be around in the comments.
I find it hard to even convince others that I am a conscious person.
Maybe consciousness is just a matter of belief, if I see this AI and believe that it's a person, then I am talking to a conscious entity.
YOU prove it is what you say, you’re the one making claims like a mentally ill moron.
And it’s easy to see why people think you’re not conscious. Plain. As. Day.
By this metric most humans are not conscious.
No kink-shaming, but this sort of thing enables self-destructive hard-to-return-from anti-social behaviour.
far from being impossible, it's the entire influencer economy. This form of social media has been extremely widespread for a decade or so running; it's probably the dominant form of social media.
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?