[Feat][Qwen3-TTS] Support streaming audio output for websocket (#1719)

Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>

tests/entrypoints/openai_api/test_serving_speech.py

@@ -1,19 +1,23 @@
 # tests/entrypoints/openai/test_serving_speech.py
+import asyncio
 import logging
 import os
 from inspect import Signature, signature
 from pathlib import Path
-from unittest.mock import MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import numpy as np
 import pytest
 import torch
-from fastapi import FastAPI, HTTPException, UploadFile
+from fastapi import FastAPI, HTTPException, Request, UploadFile
 from fastapi.params import File, Form
+from fastapi.responses import JSONResponse
 from fastapi.testclient import TestClient
 from pydantic import ValidationError
 from pytest_mock import MockerFixture
+from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
 
+from vllm_omni.entrypoints.openai import api_server as api_server_module
 from vllm_omni.entrypoints.openai.audio_utils_mixin import AudioMixin
 from vllm_omni.entrypoints.openai.protocol.audio import CreateAudio, OpenAICreateSpeechRequest
 from vllm_omni.entrypoints.openai.serving_speech import (
@@ -1052,4 +1056,33 @@ class TestAsyncOmniSupportedTasks:
         omni.stage_list = [stage]
         tasks = await omni.get_supported_tasks()
         assert "generate" in tasks
-        assert "speech" in tasks
+
+
+def test_api_server_create_speech_wraps_error_response_status():
+    handler = MagicMock()
+    handler.create_speech = AsyncMock(
+        return_value=ErrorResponse(
+            error=ErrorInfo(message="bad request", type="BadRequestError", param=None, code=400),
+        )
+    )
+
+    app = FastAPI()
+    app.state.openai_serving_speech = handler
+    scope = {
+        "type": "http",
+        "app": app,
+        "method": "POST",
+        "path": "/v1/audio/speech",
+        "headers": [],
+        "query_string": b"",
+        "client": ("127.0.0.1", 12345),
+        "server": ("testserver", 80),
+        "scheme": "http",
+    }
+    raw_request = Request(scope)
+    request = OpenAICreateSpeechRequest(input="Hello")
+
+    response = asyncio.run(api_server_module.create_speech(request, raw_request))
+
+    assert isinstance(response, JSONResponse)
+    assert response.status_code == 400