Merge pull request #519 from xinnan-tech/manage-server-edgetts-stream

edge-tts 流式写

main/xiaozhi-server/core/connection.py

@@ -184,15 +184,15 @@ class ConnectionHandler:
             await handleAudioMessage(self, message)
 
     def _initialize_components(self):
-        """加载插件"""
-        self.func_handler = FunctionHandler(self)
-
         """加载提示词"""
         self.prompt = self.config["prompt"]
         if self.private_config:
             self.prompt = self.private_config.private_config.get("prompt", self.prompt)
         self.dialogue.put(Message(role="system", content=self.prompt))
 
+        """加载插件"""
+        self.func_handler = FunctionHandler(self)
+
         """加载记忆"""
         device_id = self.headers.get("device-id", None)
         self.memory.init_memory(device_id, self.llm)

main/xiaozhi-server/core/providers/tts/edge.py

@@ -14,5 +14,14 @@ class TTSProvider(TTSProviderBase):
         return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
 
     async def text_to_speak(self, text, output_file):
-        communicate = edge_tts.Communicate(text, voice=self.voice)  # Use your preferred voice
-        await communicate.save(output_file)
+        communicate = edge_tts.Communicate(text, voice=self.voice)
+        # 确保目录存在并创建空文件
+        os.makedirs(os.path.dirname(output_file), exist_ok=True)
+        with open(output_file, 'wb') as f:
+            pass
+        
+        # 流式写入音频数据
+        with open(output_file, 'ab') as f:  # 改为追加模式避免覆盖
+            async for chunk in communicate.stream():
+                if chunk["type"] == "audio":  # 只处理音频数据块
+                    f.write(chunk["data"])