Enhance error handling in TTS generation and improve audio output compatibility by supporting both "audio" and "model_outputs" keys in response.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

examples/online_serving/qwen3_tts/openai_speech_client.py

@@ -111,6 +111,10 @@ def run_tts_generation(args) -> None:
         print(response.text)
         return
 
+    if response.content.decode("utf-8").startswith('{"error"'):
+        print(f"Error: {response.content.decode('utf-8')}")
+        return
+
     # Save audio response
     output_path = args.output or "tts_output.wav"
     with open(output_path, "wb") as f:

vllm_omni/entrypoints/openai/serving_speech.py

@@ -258,17 +258,26 @@ class OmniOpenAIServingSpeech(OpenAIServing, AudioMixin):
 
             # Extract audio from output
             # Audio can be in final_output.multimodal_output or final_output.request_output.multimodal_output
+            # Support both "audio" and "model_outputs" keys for compatibility with different models
             audio_output = None
             if hasattr(final_output, "multimodal_output") and final_output.multimodal_output:
                 audio_output = final_output.multimodal_output
-            if (not audio_output or "audio" not in audio_output) and hasattr(final_output, "request_output"):
+            if not audio_output and hasattr(final_output, "request_output"):
                 if final_output.request_output and hasattr(final_output.request_output, "multimodal_output"):
                     audio_output = final_output.request_output.multimodal_output
 
-            if not audio_output or "audio" not in audio_output:
+            # Check for audio data using either "audio" or "model_outputs" key
+            audio_key = None
+            if audio_output:
+                if "audio" in audio_output:
+                    audio_key = "audio"
+                elif "model_outputs" in audio_output:
+                    audio_key = "model_outputs"
+
+            if not audio_output or audio_key is None:
                 return self.create_error_response("TTS model did not produce audio output.")
 
-            audio_tensor = audio_output["audio"]
+            audio_tensor = audio_output[audio_key]
             sample_rate = audio_output.get("sr", 24000)
             if hasattr(sample_rate, "item"):
                 sample_rate = sample_rate.item()