clean: archive legacy stt/tts/llm services; update ARCHITECTURE.md + README.md to current stack (REST gpt-4o-transcribe, nano, sage, Honcho, incremental TTS, white noise)

Per PLAN item 6. Legacy files moved to archive/legacy-pipeline/.

archive/legacy-pipeline/tts.py

@@ -0,0 +1,31 @@
+"""Text-to-speech via OpenAI TTS API"""
+
+import logging
+from openai import AsyncOpenAI
+from config import settings
+
+logger = logging.getLogger("kira.tts")
+
+
+def _get_client() -> AsyncOpenAI:
+    return AsyncOpenAI(api_key=settings.openai_api_key)
+
+
+async def synthesize_speech(text: str, voice: str = "nova") -> bytes:
+    """Synthesize text to speech audio bytes.
+    
+    Voices available: alloy, echo, fable, nova, shimmer
+    Nova is the warmest female voice — fits Kira's personality.
+    """
+    try:
+        client = _get_client()
+        resp = await client.audio.speech.create(
+            model="tts-1",
+            voice=voice,
+            input=text,
+            response_format="opus",
+        )
+        return resp.content
+    except Exception as e:
+        logger.error(f"TTS error: {e}")
+        return b""