Wallie V2
The open-source AI streamer that actually feels alive
115 followers
The open-source AI streamer that actually feels alive
115 followers
Wallie is an open-source AI streamer that actually feels alive. It reacts to your screen, reads live chat on Twitch/YouTube/Kick, animates a Live2D avatar with real lipsync, and never repeats itself — all running locally on your machine. Swap LLM and TTS providers freely. Start free with Groq + Piper. Zero cloud lock-in.
Wallie V2
the reacts to your screen feature is the interesting differentiator here. most AI streamers just respond to chat which is a solved problem. an avatar that can comment on what's actually happening in the game or on screen is a different kind of presence. curious how the screen reading works, is it vision model calls on a frame interval or something else, and what the latency looks like between something happening on screen and Wallie actually reacting to it
Wallie V2
@ansari_adin Vision runs on a frame interval, yeah. mss captures the screen, perceptual hash (pHash) detects meaningful changes, and if the delta clears the threshold, it fires a vision model call with the current frame. The interval and sensitivity are configurable from the dashboard.
Latency from screen event to spoken reaction: typically 2–4 seconds end to end, depending on the LLM provider. Groq + Llama-4 Scout gets you the fastest loop (~1.5–2s). Claude Sonnet is slower on raw latency but produces better reactions — especially for things like recognizing game UI, character names, or anything that requires IP/context knowledge.
The attention engine also means not every screen change triggers a full reaction. The model probabilistically assigns DEEP (22%), GLANCE (28%), TANGENT (5%), IGNORE (27%), or SILENCE (18%) — so Wallie doesn't spam reactions to every mouse move, which makes the ones that do happen feel more considered. Streak fatigue prevents the same reaction type from firing back-to-back.
Super work! is it possibly to integrate it with Gemini Live Model?
Wallie V2
@ashishkingdom Gemini is already supported as an LLM provider (Gemini 2.5 Flash and Pro, streaming + vision). You set it from the dashboard: Engine → provider: gemini, then pick your model.
Gemini Live specifically (the real-time audio/multimodal API) isn't integrated yet — that's a different API surface from the standard completions endpoint Wallie uses. It's on the roadmap conceptually (the "Hearing" item — real-time audio input), but the current TTS pipeline and single-history orchestrator design would need some rethinking to accommodate it cleanly. If you're interested in contributing, that'd be a solid PR to open.