feat(model/qwen3-tts-realtime):support instruct param, update audio ws connection auth config bear -> Bear

Author: songguocola

dashscope/audio/qwen_omni/omni_realtime.py

@@ -168,7 +168,7 @@ def _get_websocket_header(self):
         )
         headers = {
             "user-agent": ua,
-            "Authorization": "bearer " + self.apikey,
+            "Authorization": "Bearer " + self.apikey,
         }
         if self.user_headers:
             headers = {**self.user_headers, **headers}

dashscope/audio/qwen_tts_realtime/qwen_tts_realtime.py

@@ -120,7 +120,7 @@ def _get_websocket_header(self):
         )
         headers = {
             "user-agent": ua,
-            "Authorization": "bearer " + self.apikey,
+            "Authorization": "Bearer " + self.apikey,
         }
         if self.user_headers:
             headers = {**self.user_headers, **headers}
@@ -177,6 +177,8 @@ def update_session(
         bit_rate: int = None,
         language_type: str = None,
         enable_tn: bool = None,
+        instructions: str = None,
+        optimize_instructions: bool = None,
         **kwargs,
     ) -> None:
         """
@@ -206,6 +208,10 @@ def update_session(
             bit_rate for tts, support 6~510,default is 128kbps. only work on format: opus/mp3  # noqa: E501  # pylint: disable=line-too-long
         enable_tn: bool
             enable text normalization for tts, default is None
+        instructions: str
+            instructions for tts, default is None
+        optimize_instructions: bool
+            optimize_instructions for tts, default is None
         """
         self.config = {
             "voice": voice,
@@ -230,6 +236,10 @@ def update_session(
 
         if language_type is not None:
             self.config["language_type"] = language_type
+        if instructions is not None:
+            self.config["instructions"] = instructions
+        if optimize_instructions is not None:
+            self.config["optimize_instructions"] = optimize_instructions
         self.config.update(kwargs)
         self.__send_str(
             json.dumps(

dashscope/audio/tts_v2/speech_synthesizer.py

@@ -147,7 +147,7 @@ def getWebsocketHeaders(self, headers, workspace):
         )
         self.headers = {
             "user-agent": ua,
-            "Authorization": "bearer " + self.apikey,
+            "Authorization": "Bearer " + self.apikey,
         }
         if headers:
             self.headers = {**self.headers, **headers}

dashscope/multimodal/multimodal_dialog.py

@@ -445,7 +445,7 @@ def get_websocket_header(self, api_key):
         )
         self.ws_headers = {
             "User-Agent": ua,
-            "Authorization": f"bearer {api_key}",
+            "Authorization": f"Bearer {api_key}",
             "Accept": "application/json",
         }
         logger.info("websocket header: %s", self.ws_headers)

dashscope/multimodal/tingwu/tingwu_realtime.py

@@ -345,7 +345,7 @@ def get_websocket_header(self, api_key):
         )
         self.ws_headers = {
             "User-Agent": ua,
-            "Authorization": f"bearer {api_key}",
+            "Authorization": f"Bearer {api_key}",
             "Accept": "application/json",
         }
         logger.info("websocket header: %s", self.ws_headers)