Merge 952316c1ed into 91ac460799

api/services/pipecat/inworld_tts.py

@@ -0,0 +1,23 @@
+"""Inworld TTS wrapper that closes its aiohttp session in cleanup().
+
+Pipecat's InworldHttpTTSService leaves session disposal to the caller. Our
+factory creates a fresh session per service instance, so we own its close here
+to avoid leaking sockets/FDs on shutdown.
+"""
+
+import aiohttp
+
+from pipecat.services.inworld.tts import InworldHttpTTSService
+
+
+class InworldOwnedSessionTTSService(InworldHttpTTSService):
+    """InworldHttpTTSService variant that owns its aiohttp session lifecycle."""
+
+    def __init__(self, *args, aiohttp_session: aiohttp.ClientSession, **kwargs):
+        super().__init__(*args, aiohttp_session=aiohttp_session, **kwargs)
+        self._owned_session = aiohttp_session
+
+    async def cleanup(self):
+        await super().cleanup()
+        if not self._owned_session.closed:
+            await self._owned_session.close()

api/services/pipecat/service_factory.py

@@ -7,6 +7,7 @@ from loguru import logger
 
 from api.constants import MPS_API_URL
 from api.services.configuration.registry import ServiceProviders
+from api.services.pipecat.inworld_tts import InworldOwnedSessionTTSService
 from api.services.pipecat.minimax_tts import MiniMaxOwnedSessionTTSService
 from api.utils.url_security import validate_user_configured_service_url
 from pipecat.services.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
@@ -38,6 +39,7 @@ from pipecat.services.google.vertex.llm import (
     GoogleVertexLLMService,
     GoogleVertexLLMSettings,
 )
+from pipecat.services.inworld.tts import InworldTTSSettings
 from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
 from pipecat.services.minimax.llm import MiniMaxLLMService
 from pipecat.services.minimax.tts import MiniMaxTTSSettings
@@ -398,6 +400,28 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
             skip_aggregator_types=["recording_router", "recording"],
             silence_time_s=1.0,
         )
+    elif user_config.tts.provider == ServiceProviders.INWORLD.value:
+        voice = getattr(user_config.tts, "voice", None) or "Ashley"
+        model = getattr(user_config.tts, "model", None) or "inworld-tts-2"
+        speed = getattr(user_config.tts, "speed", None)
+        language = getattr(user_config.tts, "language", None) or "en-US"
+        delivery_mode = getattr(user_config.tts, "delivery_mode", None) or "BALANCED"
+        session = aiohttp.ClientSession()
+        return InworldOwnedSessionTTSService(
+            api_key=user_config.tts.api_key,
+            aiohttp_session=session,
+            streaming=True,
+            settings=InworldTTSSettings(
+                voice=voice,
+                model=model,
+                language=language,
+                speaking_rate=speed,
+                delivery_mode=delivery_mode,
+            ),
+            text_filters=[xml_function_tag_filter],
+            skip_aggregator_types=["recording_router", "recording"],
+            silence_time_s=1.0,
+        )
     elif user_config.tts.provider == ServiceProviders.DOGRAH.value:
         # Convert HTTP URL to WebSocket URL for TTS
         base_url = MPS_API_URL.replace("http://", "ws://").replace("https://", "wss://")