Search results

skill code: import multiprocessing from DLC.vtuber_renderer import vtuber_process from LivinGrimoirePacket.LivinGrimoire import Skill class DiPetCycle(Skill): def __init__(self): super().__init__() # Start pygame renderer in a SEPARATE PROCESS self.cmd_queue =...

update 2, image on bottom left, mouse unstuck: import pygame import time import ctypes def vtuber_process(cmd_queue): pygame.init() # Load frames idle = pygame.image.load("idle.png") talk = pygame.image.load("talk.png") blink = pygame.image.load("blink.png") current =...

update renderer: import pygame import time def vtuber_process(cmd_queue): pygame.init() # Load frames idle = pygame.image.load("idle.png") talk = pygame.image.load("talk.png") blink = pygame.image.load("blink.png") current = idle # Force a fixed window size...

import sounddevice as sd import numpy as np import threading import time class LoudDetector: # Global static variable is_loud = False @staticmethod def get_is_loud(): temp = LoudDetector.is_loud LoudDetector.is_loud = False return temp def...

import sounddevice as sd import numpy as np import threading import time class LoudDetector: # Global static variable is_loud = False def __init__(self, threshold=0.35, cooldown=0.5): self.threshold = threshold self.cooldown = cooldown self._thread = None...

🧩 GOAL A desktop pet / VTuber window that: floats on the desktop animates (idle, blink, talk) stays always‑on‑top runs at 60 FPS never blocks your main program communicates with your main logic (e.g., “talk”, “blink”, “angry”, “idle”) This is the same pattern used by commercial VTuber...

yeah you can just run it via a program called pycharm and use voice commands or typing. I haven't bothered much with anime user interface cause I focus on robotics aspect, I want a bot to be the interface. at the bottom left of the forum there is an option to swap skins. looks like a paint brush.

yes, like set alarm to [time] I just optimized it for speech to text(for example saying 9:40 is recognized as 940) so I patched it. I think i'll post a demo. it also remembers so even if you restart the AI the alarm stays armed for the requested time. she alarms very cutely actualy. it also has...

fixed code: class DiAlarmer(Skill): def __init__(self): super().__init__() self.off: Responder = Responder("shut up", "stop") self._cron: Cron = Cron("", 3, 3) self.msg_extra: str = "" self.default_alarm: str = "beep beep beep"...

new STT optimized version: class DiAlarmer(Skill): def __init__(self): super().__init__() self.off: Responder = Responder("shut up", "stop") self._cron: Cron = Cron("", 3, 3) self.msg_extra: str = "" self.default_alarm: str = "beep beep beep"...

old ver: class DiAlarmer(Skill): def __init__(self): super().__init__() self.off: Responder = Responder("shut up", "stop") self._cron: Cron = Cron("", 3, 3) self.msg_extra: str = "" self.default_alarm: str = "beep beep beep" self._alarm_armed...

from difflib import SequenceMatcher def similarity(a, b): return SequenceMatcher(None, a, b).ratio()

import time class DiStopWatch(Skill): """ Stopwatch skill for voice-controlled timing. Auto-announces at each minute milestone while running. """ def __init__(self): super().__init__() self.timer = Timer() self.last_announced_minute = 0...

import time class Timer: """ A simple timer class for tracking elapsed time. Supports start, pause, resume, reset, and formatted output. """ def __init__(self): """Initialize a new timer. Not started by default.""" self._start_time = None...

unitree also seems good for kit bashing. too bad its so pricy. maybe in a year or too they will be affordable with doll features

would love to hear about the technical aspects of how you built her. a devlog thread even.