[Bugfix][Qwen3TTS] Load speaker_id/voices from model configuration (#1079)

Signed-off-by: pablo <juanz9312@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>

vllm_omni/entrypoints/openai/api_server.py

@@ -762,6 +762,25 @@ async def create_speech(request: OpenAICreateSpeechRequest, raw_request: Request
         raise HTTPException(status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)) from e
 
 
+@router.get(
+    "/v1/audio/voices",
+    responses={
+        HTTPStatus.OK.value: {"model": dict},
+        HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
+        HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
+        HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
+    },
+)
+async def list_voices(raw_request: Request):
+    """List available TTS voices/speakers from the loaded model."""
+    handler = Omnispeech(raw_request)
+    if handler is None:
+        return base(raw_request).create_error_response(message="The model does not support Speech API")
+
+    speakers = sorted(handler.supported_speakers) if handler.supported_speakers else []
+    return JSONResponse(content={"voices": speakers})
+
+
 # Health and Model endpoints for diffusion mode