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>
2026-06-26 22:02:52 +02:00
parent 9b68db9e82
commit e19831f7d5
9 changed files with 539 additions and 0 deletions
@@ -0,0 +1,45 @@
+import httpx
+from config import (
+    MC2_BASE_URL, CHAT_MODEL, VISION_MODEL,
+    MAX_RESPONSE_TOKENS, REQUEST_TIMEOUT, SYSTEM_PROMPT,
+    SCREENSHOT_ON_QUERY,
+)
+
+
+def ask(text: str, screenshot_b64: str | None = None) -> str:
+    """Schickt Text (+ optionalen Screenshot) an MC2 und gibt die Antwort zurück."""
+    use_vision = screenshot_b64 is not None and SCREENSHOT_ON_QUERY
+    model = VISION_MODEL if use_vision else CHAT_MODEL
+
+    if use_vision:
+        user_content = [
+            {"type": "text", "text": text},
+            {"type": "image_url", "image_url": {
+                "url": f"data:image/jpeg;base64,{screenshot_b64}"
+            }},
+        ]
+    else:
+        user_content = text
+
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {"role": "user", "content": user_content},
+        ],
+        "max_tokens": MAX_RESPONSE_TOKENS,
+        "stream": False,
+    }
+
+    try:
+        with httpx.Client(timeout=REQUEST_TIMEOUT) as client:
+            response = client.post(
+                f"{MC2_BASE_URL}/chat/completions",
+                json=payload,
+            )
+            response.raise_for_status()
+            return response.json()["choices"][0]["message"]["content"].strip()
+    except httpx.TimeoutException:
+        return "Entschuldigung, die Antwort hat zu lange gedauert."
+    except Exception as e:
+        return f"Verbindungsfehler: {e}"