Feat/speak module

example_apps/echo.py

@@ -1,14 +1,18 @@
 from __future__ import annotations
 
-from logging import StreamHandler, getLogger
+import logging
+import os
+from logging import getLogger
 
 from stackchan_server.app import StackChanApp
 from stackchan_server.ws_proxy import EmptyTranscriptError, WsProxy
 
-
 logger = getLogger(__name__)
-logger.addHandler(StreamHandler())
-logger.setLevel("DEBUG")
+logging.basicConfig(
+    level=os.getenv("STACKCHAN_LOG_LEVEL", "INFO"),
+    format="%(asctime)s.%(msecs)03d %(levelname)s:%(name)s:%(message)s",
+    datefmt="%H:%M:%S",
+)
 
 
 app = StackChanApp()

misc/api_test/test_cloud_sst.py

@@ -1,4 +1,3 @@
-import os
 from google.cloud import speech
 
 sst_client = speech.SpeechClient()

pyproject.toml

@@ -10,6 +10,7 @@ readme = "README.md"
 requires-python = ">=3.13"
 dependencies = [
     "fastapi>=0.128.0",
+    "google-genai>=1.59.0",
     "google-cloud-speech>=2.35.0",
     "uvicorn[standard]>=0.40.0",
     "voicevox-client>=1.1.0",
@@ -20,9 +21,7 @@ dev = [
     "ruff>=0.15.2",
     "ty>=0.0.17",
 ]
-example-gemini = [
-    "google-genai>=1.59.0",
-]
+example-gemini = []
 example-claude-agent-sdk = [
     "claude-agent-sdk>=0.1.39",
 ]

stackchan_server/app.py

@@ -7,15 +7,21 @@
 from fastapi import FastAPI, WebSocket, WebSocketDisconnect
 
 from .speech_recognition import create_speech_recognizer
-from .types import SpeechRecognizer
+from .speech_synthesis import create_speech_synthesizer
+from .types import SpeechRecognizer, SpeechSynthesizer
 from .ws_proxy import WsProxy
 
 logger = getLogger(__name__)
 
 
 class StackChanApp:
-    def __init__(self, speech_recognizer: SpeechRecognizer | None = None) -> None:
+    def __init__(
+        self,
+        speech_recognizer: SpeechRecognizer | None = None,
+        speech_synthesizer: SpeechSynthesizer | None = None,
+    ) -> None:
         self.speech_recognizer = speech_recognizer or create_speech_recognizer()
+        self.speech_synthesizer = speech_synthesizer or create_speech_synthesizer()
         self.fastapi = FastAPI(title="StackChan WebSocket Server")
         self._setup_fn: Optional[Callable[[WsProxy], Awaitable[None]]] = None
         self._talk_session_fn: Optional[Callable[[WsProxy], Awaitable[None]]] = None
@@ -38,7 +44,11 @@ def talk_session(self, fn: Callable[["WsProxy"], Awaitable[None]]):
 
     async def _handle_ws(self, websocket: WebSocket) -> None:
         await websocket.accept()
-        proxy = WsProxy(websocket, speech_recognizer=self.speech_recognizer)
+        proxy = WsProxy(
+            websocket,
+            speech_recognizer=self.speech_recognizer,
+            speech_synthesizer=self.speech_synthesizer,
+        )
         await proxy.start()
         try:
             if self._setup_fn: