Funktioniert

entrypoint.sh

@@ -6,8 +6,37 @@
 # (Reboot, Crash-Restart, manuell).
 set -e
 
-MODEL="Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"
+MODEL="${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice}"
 PORT=8091
+UI_PORT=8092
+WS_LOG_PORT=8094
+
+# --- Runtime-Patches fuer Qwen3-TTS anwenden ---
+if [ -f /patch_qwen3_tts_runtime.py ]; then
+  python3 /patch_qwen3_tts_runtime.py
+fi
+
+# --- Browser-UI im Container starten ---
+if [ -f /voice_clone_ui.py ]; then
+  python3 /voice_clone_ui.py \
+    --host 0.0.0.0 \
+    --port "$UI_PORT" \
+    --api-base "http://localhost:${PORT}" \
+    --clone-api-base "http://qwen3-tts-clone:8093" \
+    --model "$MODEL" &
+  UI_PID=$!
+  echo "[ui] Voice-Cloning-UI laeuft auf Port ${UI_PORT}"
+fi
+
+# --- WebSocket-Logging-Proxy im Container starten ---
+if [ -f /ws_log_proxy.py ]; then
+  python3 /ws_log_proxy.py \
+    --host 0.0.0.0 \
+    --port "$WS_LOG_PORT" \
+    --upstream "ws://localhost:${PORT}/v1/audio/speech/stream" &
+  WS_LOG_PID=$!
+  echo "[ws-log] Proxy laeuft auf Port ${WS_LOG_PORT}"
+fi
 
 # --- Server im Hintergrund starten ---
 vllm-omni serve "$MODEL" \
@@ -38,4 +67,5 @@ SERVER_PID=$!
 ) &
 
 # --- Auf den Server-Prozess warten (PID 1 Signalweiterleitung) ---
+trap 'kill "$SERVER_PID" "${UI_PID:-}" "${WS_LOG_PID:-}" 2>/dev/null || true' TERM INT
 wait "$SERVER_PID"