Hi HN, I built Beni (https://thebeni.ai ), a web app for real-time video calls with an AI companion.

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.

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?

What are you using for tts/stt/models?

This is cool.

This is disturbing.

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.