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

ai-patient-onboarding/app/services/voice_service.py

@@ -99,9 +99,11 @@ class VoiceService:
         self,
         text: str,
         language_code: str = "en-IN",
+        audio_id: str | None = None,
     ) -> tuple[str, bytes]:
         lang_prefix = language_code.lower()[:2]
-        audio_id = f"aud_{uuid4().hex[:12]}"
+        if not audio_id:
+            audio_id = f"aud_{uuid4().hex[:12]}"
 
         # Clean punctuation and brackets before synthesis
         cleaned_text = (
@@ -121,8 +123,8 @@ class VoiceService:
             and lang_prefix in ["ta", "hi", "te", "kn", "bn", "mr", "gu", "ml", "pa", "od", "en"]
         ):
             try:
-                speaker = "kavya" if lang_prefix in ["ta", "hi", "te", "kn"] else "gokul"
-                async with httpx2.AsyncClient(timeout=5.0) as client:
+                speaker = "kavya"
+                async with httpx2.AsyncClient(timeout=6.0) as client:
                     headers = {
                         "api-subscription-key": self.sarvam_key,
                         "Content-Type": "application/json",
@@ -153,11 +155,11 @@ class VoiceService:
 
         # 2. Use OpenAI TTS
         if self.openai_key and self.openai_key.strip() not in ["your_openai_api_key", "your_openai_key", ""]:
-            client = AsyncOpenAI(api_key=self.openai_key, timeout=5.0)
+            client = AsyncOpenAI(api_key=self.openai_key, timeout=6.0)
             try:
                 response = await client.audio.speech.create(
                     model="tts-1",
-                    voice="shimmer",
+                    voice="nova",
                     input=cleaned_text,
                     speed=1.0,
                 )
@@ -176,6 +178,15 @@ class VoiceService:
         file_path.write_bytes(audio_data)
         return audio_id, audio_data
 
+    async def synthesize_to_file(
+        self,
+        audio_id: str,
+        text: str,
+        language_code: str = "en-IN",
+    ) -> bytes:
+        _, audio_data = await self.text_to_speech(text, language_code=language_code, audio_id=audio_id)
+        return audio_data
+
     def _generate_fallback_wav(self) -> bytes:
         buf = io.BytesIO()
         with wave.open(buf, "wb") as wf: