fix: Use scribe_v2_realtime model for ElevenLabs STT (streaming mode)

scribe_v1 (REST) sets streaming=False, incompatible with livekit-agents 1.4 AgentSession.
scribe_v2_realtime uses WebSocket streaming (confirmed working with Starter plan).
Removes separate _stt_session aiohttp client.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

voice.py

@@ -231,7 +231,7 @@ class VoiceSession:
         self.session = None
         self._task = None
         self._http_session = None
-        self._stt_session = None
+        self._stt_session = None  # kept for cleanup compat
         self._caller_key: bytes | None = None
         self._caller_identity: str | None = None
         self._caller_all_keys: dict = {}  # {index: bytes} — all caller keys by index
@@ -555,10 +555,9 @@ class VoiceSession:
 
             # Voice pipeline — George (British male, multilingual DE/EN)
             self._http_session = aiohttp.ClientSession()
-            self._stt_session = aiohttp.ClientSession()  # separate session avoids WS/HTTP conflicts
             voice_id = os.environ.get("ELEVENLABS_VOICE_ID", DEFAULT_VOICE_ID)
             self.session = AgentSession(
-                stt=elevenlabs.STT(api_key=ELEVENLABS_KEY, http_session=self._stt_session),
+                stt=elevenlabs.STT(api_key=ELEVENLABS_KEY, model_id="scribe_v2_realtime"),
                 llm=lk_openai.LLM(base_url=LITELLM_URL, api_key=LITELLM_KEY, model=self.model),
                 tts=elevenlabs.TTS(voice_id=voice_id, model="eleven_multilingual_v2",
                                    api_key=ELEVENLABS_KEY, http_session=self._http_session),