feat: add streaming STT service with Whisper backend

- stt_streaming.py: HTTP-based STT using external Whisper service
- stt_streaming_local.py: ROCm-based local Whisper inference
- Voice Activity Detection (VAD) with WebRTC
- Interrupt detection for barge-in support
- Session state management (listening/responding)
- OpenTelemetry instrumentation with HyperDX support
- Dockerfile variants for HTTP and ROCm deployments

healthcheck.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+"""
+Health check script for Kubernetes probes
+Verifies NATS connectivity
+"""
+import sys
+import os
+import asyncio
+
+import nats
+
+NATS_URL = os.environ.get("NATS_URL", "nats://nats.ai-ml.svc.cluster.local:4222")
+
+
+async def check_health():
+    """Check if service can connect to NATS."""
+    try:
+        nc = await asyncio.wait_for(nats.connect(NATS_URL), timeout=5.0)
+        await nc.close()
+        return True
+    except Exception as e:
+        print(f"Health check failed: {e}", file=sys.stderr)
+        return False
+
+
+if __name__ == "__main__":
+    result = asyncio.run(check_health())
+    sys.exit(0 if result else 1)