feat: implement voice-based patient onboarding pipeline with AI orchestration, multi-language STT/TTS support, and clinical state extraction.

ai-patient-onboarding/app/api/onboarding.py

@@ -33,6 +33,7 @@ from app.services.patient_submission_service import (
 from app.services.result_extraction_service import (
     ResultExtractionService,
 )
+from app.services.voice_service import VoiceService
 
 
 router = APIRouter(
@@ -73,11 +74,10 @@ async def start_onboarding(
     # Initialize empty state
     onboarding_service.get_state(db, session_id)
 
-    greeting_msg = (
-        f"Hello {request.patient.name or 'there'}, "
-        "welcome to CureSelect Healthcare. "
-        "I'll ask you a few questions to understand "
-        "your current health concern. Shall we begin?"
+    voice_service = VoiceService()
+    greeting_msg = voice_service.get_initial_greeting(
+        request.patient.name,
+        request.language,
     )
 
     # Save initial assistant greeting