diff --git a/swagger/docs.go b/swagger/docs.go
index afdeb03d..1a5943c4 100644
--- a/swagger/docs.go
+++ b/swagger/docs.go
@@ -774,6 +774,33 @@ const docTemplate = `{
                     }
                 }
             }
+        },
+        "/vad": {
+            "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "summary": "Detect voice fragments in an audio stream",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.VADRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/proto.VADResponse"
+                        }
+                    }
+                }
+            }
         }
     },
     "definitions": {
@@ -1207,6 +1234,28 @@ const docTemplate = `{
                 "StatusResponse_ERROR"
             ]
         },
+        "proto.VADResponse": {
+            "type": "object",
+            "properties": {
+                "segments": {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/proto.VADSegment"
+                    }
+                }
+            }
+        },
+        "proto.VADSegment": {
+            "type": "object",
+            "properties": {
+                "end": {
+                    "type": "number"
+                },
+                "start": {
+                    "type": "number"
+                }
+            }
+        },
         "schema.BackendMonitorRequest": {
             "type": "object",
             "properties": {
@@ -1806,6 +1855,23 @@ const docTemplate = `{
                     "type": "string"
                 }
             }
+        },
+        "schema.VADRequest": {
+            "description": "VAD request body",
+            "type": "object",
+            "properties": {
+                "audio": {
+                    "description": "model name or full path",
+                    "type": "array",
+                    "items": {
+                        "type": "number"
+                    }
+                },
+                "model": {
+                    "description": "model name or full path",
+                    "type": "string"
+                }
+            }
         }
     },
     "securityDefinitions": {
diff --git a/swagger/swagger.json b/swagger/swagger.json
index f3cfd2ca..dc902e11 100644
--- a/swagger/swagger.json
+++ b/swagger/swagger.json
@@ -767,6 +767,33 @@
                     }
                 }
             }
+        },
+        "/vad": {
+            "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "summary": "Detect voice fragments in an audio stream",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.VADRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/proto.VADResponse"
+                        }
+                    }
+                }
+            }
         }
     },
     "definitions": {
@@ -1200,6 +1227,28 @@
                 "StatusResponse_ERROR"
             ]
         },
+        "proto.VADResponse": {
+            "type": "object",
+            "properties": {
+                "segments": {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/proto.VADSegment"
+                    }
+                }
+            }
+        },
+        "proto.VADSegment": {
+            "type": "object",
+            "properties": {
+                "end": {
+                    "type": "number"
+                },
+                "start": {
+                    "type": "number"
+                }
+            }
+        },
         "schema.BackendMonitorRequest": {
             "type": "object",
             "properties": {
@@ -1799,6 +1848,23 @@
                     "type": "string"
                 }
             }
+        },
+        "schema.VADRequest": {
+            "description": "VAD request body",
+            "type": "object",
+            "properties": {
+                "audio": {
+                    "description": "model name or full path",
+                    "type": "array",
+                    "items": {
+                        "type": "number"
+                    }
+                },
+                "model": {
+                    "description": "model name or full path",
+                    "type": "string"
+                }
+            }
         }
     },
     "securityDefinitions": {
diff --git a/swagger/swagger.yaml b/swagger/swagger.yaml
index 840a7dda..a447f7cc 100644
--- a/swagger/swagger.yaml
+++ b/swagger/swagger.yaml
@@ -295,6 +295,20 @@ definitions:
     - StatusResponse_BUSY
     - StatusResponse_READY
     - StatusResponse_ERROR
+  proto.VADResponse:
+    properties:
+      segments:
+        items:
+          $ref: '#/definitions/proto.VADSegment'
+        type: array
+    type: object
+  proto.VADSegment:
+    properties:
+      end:
+        type: number
+      start:
+        type: number
+    type: object
   schema.BackendMonitorRequest:
     properties:
       model:
@@ -701,6 +715,18 @@ definitions:
       type:
         type: string
     type: object
+  schema.VADRequest:
+    description: VAD request body
+    properties:
+      audio:
+        description: model name or full path
+        items:
+          type: number
+        type: array
+      model:
+        description: model name or full path
+        type: string
+    type: object
 info:
   contact:
     name: LocalAI
@@ -1188,6 +1214,23 @@ paths:
           schema:
             $ref: '#/definitions/schema.TokenizeResponse'
       summary: Tokenize the input.
+  /vad:
+    post:
+      consumes:
+      - application/json
+      parameters:
+      - description: query params
+        in: body
+        name: request
+        required: true
+        schema:
+          $ref: '#/definitions/schema.VADRequest'
+      responses:
+        "200":
+          description: Response
+          schema:
+            $ref: '#/definitions/proto.VADResponse'
+      summary: Detect voice fragments in an audio stream
 securityDefinitions:
   BearerAuth:
     in: header