Feat: Hermes Voice Client (Wake Word + STT + Vision + TTS)

Windows-Desktop-Script: Energy VAD + Whisper Wake Detection,
faster-whisper STT, mss Screen Capture, MC2 Vision/Chat API,
Edge TTS Ausgabe, pystray System Tray. Kein Account nötig —
Wake Word frei konfigurierbar via WAKE_WORDS in config.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-26 22:02:52 +02:00
parent 9b68db9e82
commit e19831f7d5
9 changed files with 539 additions and 0 deletions
+58
View File
@@ -0,0 +1,58 @@
import asyncio
import os
import tempfile
import threading
import pygame
import edge_tts
from config import TTS_VOICE, TTS_RATE, TTS_PITCH
pygame.mixer.init()
_stop_event = threading.Event()
def stop_speaking():
"""Unterbricht laufende Sprachausgabe (z.B. wenn User spricht)."""
_stop_event.set()
pygame.mixer.music.stop()
def speak(text: str):
"""Text → Edge TTS → Lautsprecher. Blockiert bis fertig oder unterbrochen."""
_stop_event.clear()
async def _run():
with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as f:
tmp_path = f.name
communicate = edge_tts.Communicate(text, TTS_VOICE, rate=TTS_RATE, pitch=TTS_PITCH)
await communicate.save(tmp_path)
if _stop_event.is_set():
os.unlink(tmp_path)
return
pygame.mixer.music.load(tmp_path)
pygame.mixer.music.play()
while pygame.mixer.music.get_busy():
if _stop_event.is_set():
pygame.mixer.music.stop()
break
pygame.time.wait(50)
os.unlink(tmp_path)
asyncio.run(_run())
def play_ding():
"""Kurzer Aktivierungs-Ton (440 Hz, 120ms)."""
import numpy as np
sample_rate = 44100
duration = 0.12
t = np.linspace(0, duration, int(sample_rate * duration), False)
wave = (np.sin(2 * np.pi * 440 * t) * 0.3 * 32767).astype(np.int16)
stereo = np.column_stack([wave, wave])
sound = pygame.sndarray.make_sound(stereo)
sound.play()
pygame.time.wait(int(duration * 1000) + 20)