Merge branch 'main' of https://github.com/dograh-hq/dograh

api/services/pipecat/minimax_tts.py

@@ -0,0 +1,23 @@
+"""MiniMax TTS wrapper that closes its aiohttp session in cleanup().
+
+Pipecat's MiniMaxHttpTTSService 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.minimax.tts import MiniMaxHttpTTSService
+
+
+class MiniMaxOwnedSessionTTSService(MiniMaxHttpTTSService):
+    """MiniMaxHttpTTSService 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

@@ -1,10 +1,12 @@
 from typing import TYPE_CHECKING
 
+import aiohttp
 from fastapi import HTTPException
 from loguru import logger
 
 from api.constants import MPS_API_URL
 from api.services.configuration.registry import ServiceProviders
+from api.services.pipecat.minimax_tts import MiniMaxOwnedSessionTTSService
 from pipecat.services.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
 from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
 from pipecat.services.azure.llm import AzureLLMService, AzureLLMSettings
@@ -38,6 +40,8 @@ from pipecat.services.openai.stt import (
 from pipecat.services.openai.tts import OpenAITTSService, OpenAITTSSettings
 from pipecat.services.openrouter.llm import OpenRouterLLMService, OpenRouterLLMSettings
 from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
+from pipecat.services.minimax.llm import MiniMaxLLMService
+from pipecat.services.minimax.tts import MiniMaxHttpTTSService, MiniMaxTTSSettings
 from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
 from pipecat.services.sarvam.tts import SarvamTTSService, SarvamTTSSettings
 from pipecat.services.speaches.llm import SpeachesLLMService, SpeachesLLMSettings
@@ -435,6 +439,40 @@ 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.MINIMAX.value:
+        group_id = getattr(user_config.tts, "group_id", None)
+        if not group_id:
+            raise HTTPException(
+                status_code=400,
+                detail="MiniMax TTS requires a group_id. Configure it in your TTS settings.",
+            )
+        voice = getattr(user_config.tts, "voice", None) or "English_Graceful_Lady"
+        speed = getattr(user_config.tts, "speed", None) or 1.0
+
+        # Pipecat appends "?GroupId=..." to base_url as-is, so /t2a_v2 must
+        # already be in the path.
+        base_url = (
+            getattr(user_config.tts, "base_url", None)
+            or "https://api.minimax.io/v1/t2a_v2"
+        ).rstrip("/")
+        if not base_url.endswith("/t2a_v2"):
+            base_url = f"{base_url}/t2a_v2"
+
+        session = aiohttp.ClientSession()
+        return MiniMaxOwnedSessionTTSService(
+            api_key=user_config.tts.api_key,
+            group_id=group_id,
+            base_url=base_url,
+            aiohttp_session=session,
+            settings=MiniMaxTTSSettings(
+                model=user_config.tts.model,
+                voice=voice,
+                speed=speed,
+            ),
+            text_filters=[xml_function_tag_filter],
+            skip_aggregator_types=["recording_router", "recording"],
+            silence_time_s=1.0,
+        )
     else:
         raise HTTPException(
             status_code=400, detail=f"Invalid TTS provider {user_config.tts.provider}"
@@ -451,6 +489,7 @@ def create_llm_service_from_provider(
     aws_access_key: str | None = None,
     aws_secret_key: str | None = None,
     aws_region: str | None = None,
+    temperature: float | None = None,
 ):
     """Create an LLM service from explicit provider/model/api_key.
 
@@ -514,6 +553,15 @@ def create_llm_service_from_provider(
             api_key=api_key or "none",
             settings=SpeachesLLMSettings(model=model),
         )
+    elif provider == ServiceProviders.MINIMAX.value:
+        return MiniMaxLLMService(
+            api_key=api_key,
+            base_url=base_url or "https://api.minimax.io/v1",
+            settings=MiniMaxLLMService.Settings(
+                model=model,
+                temperature=temperature if temperature is not None else 1.0,
+            ),
+        )
     else:
         raise HTTPException(status_code=400, detail=f"Invalid LLM provider {provider}")
 
@@ -624,5 +672,8 @@ def create_llm_service(user_config):
         kwargs["aws_access_key"] = user_config.llm.aws_access_key
         kwargs["aws_secret_key"] = user_config.llm.aws_secret_key
         kwargs["aws_region"] = user_config.llm.aws_region
+    elif provider == ServiceProviders.MINIMAX.value:
+        kwargs["base_url"] = user_config.llm.base_url
+        kwargs["temperature"] = user_config.llm.temperature
 
     return create_llm_service_from_provider(provider, model, api_key, **kwargs)