Animalive builds characters that read the room. They follow live chat, pick what to answer, and reply out loud in under three seconds — with a voice, a face, and a personality that stays consistent.
Get in touchviewer_42: Haru, it's raining here. What are you drinking?
Haru: Hot cocoa, obviously! Rainy days are the best for it. Stay dry out there, okay?
An LLM picks and answers chat messages as they arrive, prioritizing direct questions and supporters.
Streaming text-to-speech with lip sync, and Live2D expressions that follow the mood of each reply.
Each companion has a written character that holds under pressure — no prompt leaks, no role hijacking.
A desktop studio with an instant stop button, an OBS overlay, and per-session cost and latency reports.
Our first companion is a close-up VTuber for Korean live streaming (CHZZK). The desktop app (Rust + Tauri, Vue) is in active development, with a private test broadcast as the first milestone.