update:优化唤醒词答复

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

@@ -145,10 +145,9 @@ class TTSProvider(TTSProviderBase):
         self.cluster = config.get("cluster")
         self.resource_id = config.get("resource_id")
         if config.get("private_voice"):
-            self.speaker = config.get("private_voice")
+            self.voice = config.get("private_voice")
         else:
-            self.speaker = config.get("speaker")
-        self.voice = config.get("voice")
+            self.voice = config.get("speaker")
         self.ws_url = config.get("ws_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
@@ -272,7 +271,7 @@ class TTSProvider(TTSProviderBase):
                 logger.bind(tag=TAG).error(f"WebSocket连接不存在，终止发送文本")
                 return
             # 发送文本
-            await self.send_text(self.speaker, text, self.conn.sentence_id)
+            await self.send_text(self.voice, text, self.conn.sentence_id)
             return
         except Exception as e:
             logger.bind(tag=TAG).error(f"发送TTS文本失败: {str(e)}")
@@ -302,7 +301,7 @@ class TTSProvider(TTSProviderBase):
                 event=EVENT_StartSession, sessionId=session_id
             ).as_bytes()
             payload = self.get_payload_bytes(
-                event=EVENT_StartSession, speaker=self.speaker
+                event=EVENT_StartSession, speaker=self.voice
             )
             await self.send_event(header, optional, payload)
             logger.bind(tag=TAG).info("会话启动请求已发送")

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

@@ -14,9 +14,9 @@ class TTSProvider(TTSProviderBase):
         self.api_key = config.get("api_key")
         self.model = config.get("model")
         if config.get("private_voice"):
-            self.voice_id = config.get("private_voice")
+            self.voice = config.get("private_voice")
         else:
-            self.voice_id = config.get("voice_id")
+            self.voice = config.get("voice_id")
 
         default_voice_setting = {
             "voice_id": "female-shaonv",
@@ -43,8 +43,8 @@ class TTSProvider(TTSProviderBase):
         self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
         self.timber_weights = parse_string_to_list(config.get("timber_weights"))
 
-        if self.voice_id:
-            self.voice_setting["voice_id"] = self.voice_id
+        if self.voice:
+            self.voice_setting["voice_id"] = self.voice
 
         self.host = "api.minimax.chat"
         self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"

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

@@ -19,9 +19,9 @@ class TTSProvider(TTSProviderBase):
             "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=",
         )
         if config.get("private_voice"):
-            self.voice_id = int(config.get("private_voice"))
+            self.voice = int(config.get("private_voice"))
         else:
-            self.voice_id = int(config.get("voice_id", 1695))
+            self.voice = int(config.get("voice_id", 1695))
         self.token = config.get("token")
         self.to_lang = config.get("to_lang")
         self.volume_change_dB = int(config.get("volume_change_dB", 0))
@@ -50,7 +50,7 @@ class TTSProvider(TTSProviderBase):
                 "emotion": self.emotion,
                 "format": self.format,
                 "volume_change_dB": self.volume_change_dB,
-                "voice_id": self.voice_id,
+                "voice_id": self.voice,
                 "pitch_factor": self.pitch_factor,
                 "speed_factor": self.speed_factor,
                 "token": self.token,