fix audio/wav response handling (opea-project#802)

* fix audio output

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: Spycsh

comps/cores/mega/orchestrator.py

@@ -202,10 +202,16 @@ def generate():
             if LOGFLAG:
                 logger.info(inputs)
             async with session.post(endpoint, json=inputs) as response:
-                # Parse as JSON
-                data = await response.json()
-                # post process
-                data = self.align_outputs(data, cur_node, inputs, runtime_graph, llm_parameters_dict, **kwargs)
+                if response.content_type == "audio/wav":
+                    audio_data = await response.read()
+                    data = self.align_outputs(
+                        audio_data, cur_node, inputs, runtime_graph, llm_parameters_dict, **kwargs
+                    )
+                else:
+                    # Parse as JSON
+                    data = await response.json()
+                    # post process
+                    data = self.align_outputs(data, cur_node, inputs, runtime_graph, llm_parameters_dict, **kwargs)
 
                 return data, cur_node