diff --git a/funasr/runtime/python/grpc/grpc_main_server.py b/funasr/runtime/python/grpc/grpc_main_server.py
index e862ac495..ae386faa6 100644
--- a/funasr/runtime/python/grpc/grpc_main_server.py
+++ b/funasr/runtime/python/grpc/grpc_main_server.py
@@ -10,7 +10,7 @@ def serve(args):
                         # interceptors=(AuthInterceptor('Bearer mysecrettoken'),)
                            )
       paraformer_pb2_grpc.add_ASRServicer_to_server(
-          ASRServicer(args.user_allowed, args.model, args.sample_rate, args.backend, args.onnx_dir), server)
+          ASRServicer(args.user_allowed, args.model, args.sample_rate, args.backend, args.onnx_dir, vad_model=args.vad_model, punc_model=args.punc_model), server)
       port = "[::]:" + str(args.port)
       server.add_insecure_port(port)
       server.start()
@@ -34,7 +34,16 @@ if __name__ == '__main__':
                         type=str,
                         default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                         help="model from modelscope")
-                        
+    parser.add_argument("--vad_model",
+                        type=str,
+                        default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+                        help="model from modelscope")
+    
+    parser.add_argument("--punc_model",
+                        type=str,
+                        default="",
+                        help="model from modelscope")
+    
     parser.add_argument("--sample_rate",
                         type=int,
                         default=16000,
@@ -50,6 +59,7 @@ if __name__ == '__main__':
                         type=str,
                         default="/nfs/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                         help="onnx model dir")
+    
                         
 
 
diff --git a/funasr/runtime/python/grpc/grpc_server.py b/funasr/runtime/python/grpc/grpc_server.py
index 95fe96cdb..0fdf30c73 100644
--- a/funasr/runtime/python/grpc/grpc_server.py
+++ b/funasr/runtime/python/grpc/grpc_server.py
@@ -8,7 +8,7 @@ from paraformer_pb2 import Response
 
 
 class ASRServicer(paraformer_pb2_grpc.ASRServicer):
-    def __init__(self, user_allowed, model, sample_rate, backend, onnx_dir):
+    def __init__(self, user_allowed, model, sample_rate, backend, onnx_dir, vad_model='', punc_model=''):
         print("ASRServicer init")
         self.backend = backend
         self.init_flag = 0
@@ -21,7 +21,7 @@ class ASRServicer(paraformer_pb2_grpc.ASRServicer):
                 from modelscope.utils.constant import Tasks
             except ImportError:
                 raise ImportError(f"Please install modelscope")
-            self.inference_16k_pipeline = pipeline(task=Tasks.auto_speech_recognition, model=model)
+            self.inference_16k_pipeline = pipeline(task=Tasks.auto_speech_recognition, model=model, vad_model=vad_model, punc_model=punc_model)
         elif self.backend == "onnxruntime":
             try:
                 from rapid_paraformer.paraformer_onnx import Paraformer