diff --git a/codex-rs/app-server-protocol/schema/json/ClientRequest.json b/codex-rs/app-server-protocol/schema/json/ClientRequest.json
index 1557df56f7..8a3613daa8 100644
--- a/codex-rs/app-server-protocol/schema/json/ClientRequest.json
+++ b/codex-rs/app-server-protocol/schema/json/ClientRequest.json
@@ -670,6 +670,26 @@
           "title": "InputImageContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "text": {
@@ -1251,6 +1271,26 @@
           "title": "InputImageFunctionCallOutputContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioFunctionCallOutputContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioFunctionCallOutputContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "encrypted_content": {
@@ -4864,6 +4904,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/ServerNotification.json b/codex-rs/app-server-protocol/schema/json/ServerNotification.json
index 42038ba371..db75d4a0d4 100644
--- a/codex-rs/app-server-protocol/schema/json/ServerNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/ServerNotification.json
@@ -5562,6 +5562,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
index 7588992563..4cd4636b9a 100644
--- a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
+++ b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
@@ -9012,6 +9012,26 @@
             "title": "InputImageContentItem",
             "type": "object"
           },
+          {
+            "properties": {
+              "audio_url": {
+                "type": "string"
+              },
+              "type": {
+                "enum": [
+                  "input_audio"
+                ],
+                "title": "InputAudioContentItemType",
+                "type": "string"
+              }
+            },
+            "required": [
+              "audio_url",
+              "type"
+            ],
+            "title": "InputAudioContentItem",
+            "type": "object"
+          },
           {
             "properties": {
               "text": {
@@ -10628,6 +10648,26 @@
             "title": "InputImageFunctionCallOutputContentItem",
             "type": "object"
           },
+          {
+            "properties": {
+              "audio_url": {
+                "type": "string"
+              },
+              "type": {
+                "enum": [
+                  "input_audio"
+                ],
+                "title": "InputAudioFunctionCallOutputContentItemType",
+                "type": "string"
+              }
+            },
+            "required": [
+              "audio_url",
+              "type"
+            ],
+            "title": "InputAudioFunctionCallOutputContentItem",
+            "type": "object"
+          },
           {
             "properties": {
               "encrypted_content": {
@@ -21234,6 +21274,46 @@
             "title": "LocalImageUserInput",
             "type": "object"
           },
+          {
+            "properties": {
+              "type": {
+                "enum": [
+                  "audio"
+                ],
+                "title": "AudioUserInputType",
+                "type": "string"
+              },
+              "url": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "url"
+            ],
+            "title": "AudioUserInput",
+            "type": "object"
+          },
+          {
+            "properties": {
+              "path": {
+                "type": "string"
+              },
+              "type": {
+                "enum": [
+                  "localAudio"
+                ],
+                "title": "LocalAudioUserInputType",
+                "type": "string"
+              }
+            },
+            "required": [
+              "path",
+              "type"
+            ],
+            "title": "LocalAudioUserInput",
+            "type": "object"
+          },
           {
             "properties": {
               "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json
index 7c265ebbff..2ba1134dc6 100644
--- a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json
+++ b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json
@@ -5205,6 +5205,26 @@
           "title": "InputImageContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "text": {
@@ -6821,6 +6841,26 @@
           "title": "InputImageFunctionCallOutputContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioFunctionCallOutputContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioFunctionCallOutputContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "encrypted_content": {
@@ -19013,6 +19053,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ItemCompletedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/ItemCompletedNotification.json
index 58e74d1a3c..dd8353e729 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ItemCompletedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ItemCompletedNotification.json
@@ -1378,6 +1378,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ItemStartedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/ItemStartedNotification.json
index 4244c2bb19..5e12386041 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ItemStartedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ItemStartedNotification.json
@@ -1378,6 +1378,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/RawResponseItemCompletedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/RawResponseItemCompletedNotification.json
index dad669b139..b20400d16a 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/RawResponseItemCompletedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/RawResponseItemCompletedNotification.json
@@ -97,6 +97,26 @@
           "title": "InputImageContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "text": {
@@ -185,6 +205,26 @@
           "title": "InputImageFunctionCallOutputContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioFunctionCallOutputContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioFunctionCallOutputContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "encrypted_content": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ReviewStartResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ReviewStartResponse.json
index 46bcb0ac64..1008400bc9 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ReviewStartResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ReviewStartResponse.json
@@ -1653,6 +1653,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadForkResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadForkResponse.json
index 03b4e5db33..fcdc2c6630 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadForkResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadForkResponse.json
@@ -2259,6 +2259,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadListResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadListResponse.json
index 98c2174473..0809b9c3ee 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadListResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadListResponse.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadMetadataUpdateResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadMetadataUpdateResponse.json
index b719f1dab3..17bc5bb5b6 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadMetadataUpdateResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadMetadataUpdateResponse.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadReadResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadReadResponse.json
index 8a84fae30e..dd9458d9c9 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadReadResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadReadResponse.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
index 0cd7d9ae7b..0ff306cf1b 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
@@ -159,6 +159,26 @@
           "title": "InputImageContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "text": {
@@ -247,6 +267,26 @@
           "title": "InputImageFunctionCallOutputContentItem",
           "type": "object"
         },
+        {
+          "properties": {
+            "audio_url": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "input_audio"
+              ],
+              "title": "InputAudioFunctionCallOutputContentItemType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "audio_url",
+            "type"
+          ],
+          "title": "InputAudioFunctionCallOutputContentItem",
+          "type": "object"
+        },
         {
           "properties": {
             "encrypted_content": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeResponse.json
index 8f339d196e..28081e377a 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeResponse.json
@@ -2285,6 +2285,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadRollbackResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadRollbackResponse.json
index 1c2f9f5bbc..8bd889b655 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadRollbackResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadRollbackResponse.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartResponse.json
index 1b10b34d58..e4a280e1ac 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartResponse.json
@@ -2259,6 +2259,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartedNotification.json
index ba1f718b09..35c8e432d6 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartedNotification.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadUnarchiveResponse.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadUnarchiveResponse.json
index 44ecb9f7b2..144f0d981c 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadUnarchiveResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadUnarchiveResponse.json
@@ -2050,6 +2050,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnCompletedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/TurnCompletedNotification.json
index b63f3b6eb6..554a4cff6b 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnCompletedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnCompletedNotification.json
@@ -1653,6 +1653,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json b/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
index b38792e448..477e57e43e 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
@@ -472,6 +472,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnStartResponse.json b/codex-rs/app-server-protocol/schema/json/v2/TurnStartResponse.json
index 55fb943eef..484c34b071 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnStartResponse.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnStartResponse.json
@@ -1653,6 +1653,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnStartedNotification.json b/codex-rs/app-server-protocol/schema/json/v2/TurnStartedNotification.json
index 1de6c7d92c..06fdc6e81e 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnStartedNotification.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnStartedNotification.json
@@ -1653,6 +1653,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnSteerParams.json b/codex-rs/app-server-protocol/schema/json/v2/TurnSteerParams.json
index 63317f13ba..2a3627cbd0 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnSteerParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnSteerParams.json
@@ -166,6 +166,46 @@
           "title": "LocalImageUserInput",
           "type": "object"
         },
+        {
+          "properties": {
+            "type": {
+              "enum": [
+                "audio"
+              ],
+              "title": "AudioUserInputType",
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "url"
+          ],
+          "title": "AudioUserInput",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "path": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "localAudio"
+              ],
+              "title": "LocalAudioUserInputType",
+              "type": "string"
+            }
+          },
+          "required": [
+            "path",
+            "type"
+          ],
+          "title": "LocalAudioUserInput",
+          "type": "object"
+        },
         {
           "properties": {
             "name": {
diff --git a/codex-rs/app-server-protocol/schema/typescript/ContentItem.ts b/codex-rs/app-server-protocol/schema/typescript/ContentItem.ts
index 21cd8d02f3..9e53b5fc25 100644
--- a/codex-rs/app-server-protocol/schema/typescript/ContentItem.ts
+++ b/codex-rs/app-server-protocol/schema/typescript/ContentItem.ts
@@ -3,4 +3,4 @@
 // This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
 import type { ImageDetail } from "./ImageDetail";
 
-export type ContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, } | { "type": "output_text", text: string, };
+export type ContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, } | { "type": "input_audio", audio_url: string, } | { "type": "output_text", text: string, };
diff --git a/codex-rs/app-server-protocol/schema/typescript/FunctionCallOutputContentItem.ts b/codex-rs/app-server-protocol/schema/typescript/FunctionCallOutputContentItem.ts
index cd18908145..6c2ab2afa1 100644
--- a/codex-rs/app-server-protocol/schema/typescript/FunctionCallOutputContentItem.ts
+++ b/codex-rs/app-server-protocol/schema/typescript/FunctionCallOutputContentItem.ts
@@ -7,4 +7,4 @@ import type { ImageDetail } from "./ImageDetail";
  * Responses API compatible content items that can be returned by a tool call.
  * This is a subset of ContentItem with the types we support as function call outputs.
  */
-export type FunctionCallOutputContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, } | { "type": "encrypted_content", encrypted_content: string, };
+export type FunctionCallOutputContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, } | { "type": "input_audio", audio_url: string, } | { "type": "encrypted_content", encrypted_content: string, };
diff --git a/codex-rs/app-server-protocol/schema/typescript/v2/UserInput.ts b/codex-rs/app-server-protocol/schema/typescript/v2/UserInput.ts
index 2ac37c5228..c268cb4f8d 100644
--- a/codex-rs/app-server-protocol/schema/typescript/v2/UserInput.ts
+++ b/codex-rs/app-server-protocol/schema/typescript/v2/UserInput.ts
@@ -8,4 +8,4 @@ export type UserInput = { "type": "text", text: string,
 /**
  * UI-defined spans within `text` used to render or persist special elements.
  */
-text_elements: Array<TextElement>, } | { "type": "image", detail?: ImageDetail, url: string, } | { "type": "localImage", detail?: ImageDetail, path: string, } | { "type": "skill", name: string, path: string, } | { "type": "mention", name: string, path: string, };
+text_elements: Array<TextElement>, } | { "type": "image", detail?: ImageDetail, url: string, } | { "type": "localImage", detail?: ImageDetail, path: string, } | { "type": "audio", url: string, } | { "type": "localAudio", path: string, } | { "type": "skill", name: string, path: string, } | { "type": "mention", name: string, path: string, };
diff --git a/codex-rs/app-server-protocol/src/protocol/v2/tests.rs b/codex-rs/app-server-protocol/src/protocol/v2/tests.rs
index fd2a28ddde..580a57d592 100644
--- a/codex-rs/app-server-protocol/src/protocol/v2/tests.rs
+++ b/codex-rs/app-server-protocol/src/protocol/v2/tests.rs
@@ -2545,6 +2545,12 @@ fn core_turn_item_into_thread_item_converts_supported_variants() {
                 path: PathBuf::from("local/image.png"),
                 detail: Some(ImageDetail::Original),
             },
+            CoreUserInput::Audio {
+                audio_url: "data:audio/wav;base64,AAA".to_string(),
+            },
+            CoreUserInput::LocalAudio {
+                path: PathBuf::from("local/audio.mp3"),
+            },
             CoreUserInput::Skill {
                 name: "skill-creator".to_string(),
                 path: PathBuf::from("/repo/.codex/skills/skill-creator/SKILL.md"),
@@ -2574,6 +2580,12 @@ fn core_turn_item_into_thread_item_converts_supported_variants() {
                     path: PathBuf::from("local/image.png"),
                     detail: Some(ImageDetail::Original),
                 },
+                UserInput::Audio {
+                    url: "data:audio/wav;base64,AAA".to_string(),
+                },
+                UserInput::LocalAudio {
+                    path: PathBuf::from("local/audio.mp3"),
+                },
                 UserInput::Skill {
                     name: "skill-creator".to_string(),
                     path: PathBuf::from("/repo/.codex/skills/skill-creator/SKILL.md"),
@@ -3022,7 +3034,7 @@ fn mcp_tool_call_app_context_serializes_missing_mixed_version_fields_as_null() {
 }
 
 #[test]
-fn user_input_into_core_preserves_image_detail() {
+fn user_input_into_core_preserves_media_fields() {
     assert_eq!(
         UserInput::Image {
             url: "https://example.com/image.png".to_string(),
@@ -3046,6 +3058,26 @@ fn user_input_into_core_preserves_image_detail() {
             detail: Some(ImageDetail::Original),
         }
     );
+
+    assert_eq!(
+        UserInput::Audio {
+            url: "data:audio/wav;base64,AAA".to_string(),
+        }
+        .into_core(),
+        CoreUserInput::Audio {
+            audio_url: "data:audio/wav;base64,AAA".to_string(),
+        }
+    );
+
+    assert_eq!(
+        UserInput::LocalAudio {
+            path: PathBuf::from("local/audio.mp3"),
+        }
+        .into_core(),
+        CoreUserInput::LocalAudio {
+            path: PathBuf::from("local/audio.mp3"),
+        }
+    );
 }
 
 #[test]
diff --git a/codex-rs/app-server-protocol/src/protocol/v2/turn.rs b/codex-rs/app-server-protocol/src/protocol/v2/turn.rs
index 62a289cd25..cb8473d49a 100644
--- a/codex-rs/app-server-protocol/src/protocol/v2/turn.rs
+++ b/codex-rs/app-server-protocol/src/protocol/v2/turn.rs
@@ -308,6 +308,12 @@ pub enum UserInput {
         detail: Option<ImageDetail>,
         path: PathBuf,
     },
+    Audio {
+        url: String,
+    },
+    LocalAudio {
+        path: PathBuf,
+    },
     Skill {
         name: String,
         path: PathBuf,
@@ -333,6 +339,8 @@ impl UserInput {
                 detail,
             },
             UserInput::LocalImage { path, detail } => CoreUserInput::LocalImage { path, detail },
+            UserInput::Audio { url } => CoreUserInput::Audio { audio_url: url },
+            UserInput::LocalAudio { path } => CoreUserInput::LocalAudio { path },
             UserInput::Skill { name, path } => CoreUserInput::Skill { name, path },
             UserInput::Mention { name, path } => CoreUserInput::Mention { name, path },
         }
@@ -354,6 +362,8 @@ impl From<CoreUserInput> for UserInput {
                 detail,
             },
             CoreUserInput::LocalImage { path, detail } => UserInput::LocalImage { path, detail },
+            CoreUserInput::Audio { audio_url } => UserInput::Audio { url: audio_url },
+            CoreUserInput::LocalAudio { path } => UserInput::LocalAudio { path },
             CoreUserInput::Skill { name, path } => UserInput::Skill { name, path },
             CoreUserInput::Mention { name, path } => UserInput::Mention { name, path },
             _ => unreachable!("unsupported user input variant"),
@@ -367,6 +377,8 @@ impl UserInput {
             UserInput::Text { text, .. } => text.chars().count(),
             UserInput::Image { .. }
             | UserInput::LocalImage { .. }
+            | UserInput::Audio { .. }
+            | UserInput::LocalAudio { .. }
             | UserInput::Skill { .. }
             | UserInput::Mention { .. } => 0,
         }
diff --git a/codex-rs/app-server/tests/suite/v2/thread_read.rs b/codex-rs/app-server/tests/suite/v2/thread_read.rs
index 482a6ff1dd..ed23ac88b5 100644
--- a/codex-rs/app-server/tests/suite/v2/thread_read.rs
+++ b/codex-rs/app-server/tests/suite/v2/thread_read.rs
@@ -2078,6 +2078,8 @@ fn turn_user_texts(turns: &[codex_app_server_protocol::Turn]) -> Vec<&str> {
                 UserInput::Text { text, .. } => Some(text.as_str()),
                 UserInput::Image { .. }
                 | UserInput::LocalImage { .. }
+                | UserInput::Audio { .. }
+                | UserInput::LocalAudio { .. }
                 | UserInput::Skill { .. }
                 | UserInput::Mention { .. } => None,
             },
diff --git a/codex-rs/core/src/agent/control.rs b/codex-rs/core/src/agent/control.rs
index 2c944ad7f6..749c3f3f4b 100644
--- a/codex-rs/core/src/agent/control.rs
+++ b/codex-rs/core/src/agent/control.rs
@@ -750,6 +750,10 @@ pub(crate) fn render_input_preview(input: &[UserInput]) -> String {
             UserInput::LocalImage { path, .. } => {
                 format!("[local_image:{}]", path.display())
             }
+            UserInput::Audio { .. } => "[audio]".to_string(),
+            UserInput::LocalAudio { path } => {
+                format!("[local_audio:{}]", path.display())
+            }
             UserInput::Skill { name, path, .. } => {
                 format!("[skill:${name}]({})", path.display())
             }
diff --git a/codex-rs/core/src/agent/control_tests.rs b/codex-rs/core/src/agent/control_tests.rs
index 97016c0bd4..6d4cbc7ebd 100644
--- a/codex-rs/core/src/agent/control_tests.rs
+++ b/codex-rs/core/src/agent/control_tests.rs
@@ -252,7 +252,7 @@ fn has_subagent_notification(history_items: &[ResponseItem]) -> bool {
             ContentItem::InputText { text } | ContentItem::OutputText { text } => {
                 SubagentNotification::matches_text(text)
             }
-            ContentItem::InputImage { .. } => false,
+            ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => false,
         })
     })
 }
@@ -267,7 +267,7 @@ fn history_contains_text(history_items: &[ResponseItem], needle: &str) -> bool {
             ContentItem::InputText { text } | ContentItem::OutputText { text } => {
                 text.contains(needle)
             }
-            ContentItem::InputImage { .. } => false,
+            ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => false,
         })
     })
 }
@@ -290,7 +290,9 @@ fn history_contains_assistant_inter_agent_communication(
                     .as_ref()
                     == Some(expected)
             }
-            ContentItem::InputText { .. } | ContentItem::InputImage { .. } => false,
+            ContentItem::InputText { .. }
+            | ContentItem::InputImage { .. }
+            | ContentItem::InputAudio { .. } => false,
         })
     })
 }
diff --git a/codex-rs/core/src/compact.rs b/codex-rs/core/src/compact.rs
index 599f518aa0..a082c7d20a 100644
--- a/codex-rs/core/src/compact.rs
+++ b/codex-rs/core/src/compact.rs
@@ -484,7 +484,7 @@ pub fn content_items_to_text(content: &[ContentItem]) -> Option<String> {
                     pieces.push(text.as_str());
                 }
             }
-            ContentItem::InputImage { .. } => {}
+            ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => {}
         }
     }
     if pieces.is_empty() {
diff --git a/codex-rs/core/src/compact_remote_v2.rs b/codex-rs/core/src/compact_remote_v2.rs
index 58cbfb1218..a0bb9e11ae 100644
--- a/codex-rs/core/src/compact_remote_v2.rs
+++ b/codex-rs/core/src/compact_remote_v2.rs
@@ -516,7 +516,7 @@ fn message_text_token_count(item: &ResponseItem) -> usize {
             ContentItem::InputText { text } | ContentItem::OutputText { text } => {
                 approx_token_count(text)
             }
-            ContentItem::InputImage { .. } => 0,
+            ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => 0,
         })
         .sum()
 }
@@ -556,7 +556,9 @@ fn truncate_message_text_to_token_budget(
                     truncated_content.push(content_item);
                 }
             }
-            ContentItem::InputImage { .. } => truncated_content.push(content_item),
+            ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => {
+                truncated_content.push(content_item);
+            }
         }
     }
 
diff --git a/codex-rs/core/src/event_mapping.rs b/codex-rs/core/src/event_mapping.rs
index 6a474567b3..f3b714c8ef 100644
--- a/codex-rs/core/src/event_mapping.rs
+++ b/codex-rs/core/src/event_mapping.rs
@@ -113,6 +113,11 @@ fn parse_user_message(message: &[ContentItem]) -> Option<UserMessageItem> {
                     detail: *detail,
                 });
             }
+            ContentItem::InputAudio { audio_url } => {
+                content.push(UserInput::Audio {
+                    audio_url: audio_url.clone(),
+                });
+            }
             ContentItem::OutputText { text } => {
                 warn!("Output text in user message: {}", text);
             }
diff --git a/codex-rs/core/src/guardian/tests.rs b/codex-rs/core/src/guardian/tests.rs
index 34ea6acad9..bc8eaf8b69 100644
--- a/codex-rs/core/src/guardian/tests.rs
+++ b/codex-rs/core/src/guardian/tests.rs
@@ -345,7 +345,7 @@ fn response_item_contains_message_text(item: &ResponseItem, needle: &str) -> boo
     };
     content.iter().any(|item| match item {
         ContentItem::InputText { text } | ContentItem::OutputText { text } => text.contains(needle),
-        ContentItem::InputImage { .. } => false,
+        ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => false,
     })
 }
 
diff --git a/codex-rs/core/src/hook_runtime.rs b/codex-rs/core/src/hook_runtime.rs
index 3adbea420c..c9fe099332 100644
--- a/codex-rs/core/src/hook_runtime.rs
+++ b/codex-rs/core/src/hook_runtime.rs
@@ -844,7 +844,9 @@ mod tests {
                             .iter()
                             .map(|item| match item {
                                 ContentItem::InputText { text } => text.as_str(),
-                                ContentItem::InputImage { .. } | ContentItem::OutputText { .. } => {
+                                ContentItem::InputImage { .. }
+                                | ContentItem::InputAudio { .. }
+                                | ContentItem::OutputText { .. } => {
                                     panic!("expected input text content, got {item:?}")
                                 }
                             })
diff --git a/codex-rs/core/src/tools/handlers/multi_agents_spec.rs b/codex-rs/core/src/tools/handlers/multi_agents_spec.rs
index f888811052..9e74b01a50 100644
--- a/codex-rs/core/src/tools/handlers/multi_agents_spec.rs
+++ b/codex-rs/core/src/tools/handlers/multi_agents_spec.rs
@@ -559,10 +559,14 @@ fn create_collab_input_items_schema() -> JsonSchema {
             "image_url".to_string(),
             JsonSchema::string(Some("Image URL when type is image.".to_string())),
         ),
+        (
+            "audio_url".to_string(),
+            JsonSchema::string(Some("Audio URL when type is audio.".to_string())),
+        ),
         (
             "path".to_string(),
             JsonSchema::string(Some(
-                "Path when type is local_image/skill, or structured mention target such as app://<connector-id> or plugin://<plugin-name>@<marketplace-name> when type is mention."
+                "Path when type is local_image/local_audio/skill, or structured mention target such as app://<connector-id> or plugin://<plugin-name>@<marketplace-name> when type is mention."
                     .to_string(),
             )),
         ),
diff --git a/codex-rs/ext/image-generation/src/tool.rs b/codex-rs/ext/image-generation/src/tool.rs
index 3c73aaa5d4..adb2e0261f 100644
--- a/codex-rs/ext/image-generation/src/tool.rs
+++ b/codex-rs/ext/image-generation/src/tool.rs
@@ -363,7 +363,9 @@ fn recent_images(history: &[ResponseItem], count: usize) -> Vec<ImageUrl> {
             ResponseItem::Message { content, .. } => {
                 image_urls.extend(content.iter().rev().filter_map(|item| match item {
                     ContentItem::InputImage { image_url, .. } => Some(image_url.clone()),
-                    ContentItem::InputText { .. } | ContentItem::OutputText { .. } => None,
+                    ContentItem::InputText { .. }
+                    | ContentItem::InputAudio { .. }
+                    | ContentItem::OutputText { .. } => None,
                 }));
             }
             ResponseItem::FunctionCallOutput {
@@ -417,6 +419,7 @@ fn output_image_urls(output: &FunctionCallOutputPayload) -> impl Iterator<Item =
         .filter_map(|item| match item {
             FunctionCallOutputContentItem::InputImage { image_url, .. } => Some(image_url.clone()),
             FunctionCallOutputContentItem::InputText { .. }
+            | FunctionCallOutputContentItem::InputAudio { .. }
             | FunctionCallOutputContentItem::EncryptedContent { .. } => None,
         })
 }
diff --git a/codex-rs/ext/skills/src/selection.rs b/codex-rs/ext/skills/src/selection.rs
index a708b18d6c..946115e5c3 100644
--- a/codex-rs/ext/skills/src/selection.rs
+++ b/codex-rs/ext/skills/src/selection.rs
@@ -36,7 +36,11 @@ pub(crate) fn collect_explicit_skill_mentions(
                 blocked_plain_names.insert(name.clone());
                 select_by_path(catalog, path, &mut seen, &mut selected);
             }
-            UserInput::Text { .. } | UserInput::Image { .. } | UserInput::LocalImage { .. } => {}
+            UserInput::Text { .. }
+            | UserInput::Image { .. }
+            | UserInput::LocalImage { .. }
+            | UserInput::Audio { .. }
+            | UserInput::LocalAudio { .. } => {}
             UserInput::Mention { .. } => {}
             _ => {}
         }
diff --git a/codex-rs/protocol/src/models.rs b/codex-rs/protocol/src/models.rs
index 56d0bce102..1774921288 100644
--- a/codex-rs/protocol/src/models.rs
+++ b/codex-rs/protocol/src/models.rs
@@ -718,6 +718,9 @@ pub enum ContentItem {
         #[ts(optional)]
         detail: Option<ImageDetail>,
     },
+    InputAudio {
+        audio_url: String,
+    },
     OutputText {
         text: String,
     },
@@ -1334,16 +1337,37 @@ fn should_serialize_reasoning_content(content: &Option<Vec<ReasoningItemContent>
     }
 }
 
-fn local_image_error_placeholder(
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum LocalMediaKind {
+    Audio,
+    Image,
+}
+
+impl LocalMediaKind {
+    fn name(self) -> &'static str {
+        match self {
+            Self::Audio => "audio",
+            Self::Image => "image",
+        }
+    }
+}
+
+fn local_media_error_placeholder(
     path: &std::path::Path,
     error: impl std::fmt::Display,
+    media_kind: LocalMediaKind,
 ) -> ContentItem {
+    let media_name = media_kind.name();
+    let path = path.display();
     ContentItem::InputText {
-        text: format!(
-            "Codex could not read the local image at `{}`: {}",
-            path.display(),
-            error
-        ),
+        text: format!("Codex could not read the local {media_name} at `{path}`: {error}"),
+    }
+}
+
+fn local_media_kind_unsupported(media_kind: LocalMediaKind) -> ContentItem {
+    let media_name = media_kind.name();
+    ContentItem::InputText {
+        text: format!("Codex does not support local {media_name} input yet."),
     }
 }
 
@@ -1431,13 +1455,21 @@ pub fn local_image_content_items_with_label_number(
             | ImageProcessingError::Encode { .. }
             | ImageProcessingError::InvalidDataUrl { .. }
             | ImageProcessingError::ImageTooLarge { .. } => {
-                vec![local_image_error_placeholder(path, &err)]
+                vec![local_media_error_placeholder(
+                    path,
+                    &err,
+                    LocalMediaKind::Image,
+                )]
             }
             ImageProcessingError::Decode { .. } if err.is_invalid_image() => {
                 vec![invalid_image_error_placeholder(path, &err)]
             }
             ImageProcessingError::Decode { .. } => {
-                vec![local_image_error_placeholder(path, &err)]
+                vec![local_media_error_placeholder(
+                    path,
+                    &err,
+                    LocalMediaKind::Image,
+                )]
             }
             ImageProcessingError::UnsupportedImageFormat { mime } => {
                 vec![unsupported_image_error_placeholder(path, mime)]
@@ -1647,9 +1679,20 @@ impl ResponseInputItem {
                                     detail,
                                 ),
                             },
-                            Err(err) => vec![local_image_error_placeholder(&path, err)],
+                            Err(err) => vec![local_media_error_placeholder(
+                                &path,
+                                err,
+                                LocalMediaKind::Image,
+                            )],
                         }
                     }
+                    UserInput::Audio { .. } => vec![ContentItem::InputText {
+                        text: "Codex does not support audio input yet.".to_string(),
+                    }],
+                    // TODO: Load local audio inputs once they are supported.
+                    UserInput::LocalAudio { .. } => {
+                        vec![local_media_kind_unsupported(LocalMediaKind::Audio)]
+                    }
                     UserInput::Skill { .. } | UserInput::Mention { .. } => Vec::new(), // Tool bodies are injected later in core
                 })
                 .collect::<Vec<ContentItem>>(),
@@ -1707,6 +1750,10 @@ pub enum FunctionCallOutputContentItem {
         #[ts(optional)]
         detail: Option<ImageDetail>,
     },
+    // Do not rename, these are serialized and used directly in the responses API.
+    InputAudio {
+        audio_url: String,
+    },
     EncryptedContent {
         encrypted_content: String,
     },
@@ -1734,6 +1781,7 @@ pub fn function_call_output_content_items_to_text(
             }
             FunctionCallOutputContentItem::InputText { .. }
             | FunctionCallOutputContentItem::InputImage { .. }
+            | FunctionCallOutputContentItem::InputAudio { .. }
             | FunctionCallOutputContentItem::EncryptedContent { .. } => None,
         })
         .collect::<Vec<_>>();
@@ -3192,6 +3240,44 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn replaces_unsupported_audio_user_input_with_placeholder() {
+        let item = ResponseInputItem::from(vec![UserInput::Audio {
+            audio_url: "data:audio/wav;base64,abc".to_string(),
+        }]);
+
+        assert_eq!(
+            item,
+            ResponseInputItem::Message {
+                role: "user".to_string(),
+                content: vec![ContentItem::InputText {
+                    text: "Codex does not support audio input yet.".to_string(),
+                }],
+                phase: None,
+            }
+        );
+    }
+
+    #[test]
+    fn replaces_unsupported_local_audio_user_input_with_placeholder() -> Result<()> {
+        let item = ResponseInputItem::from(vec![UserInput::LocalAudio {
+            path: "sample.mp3".into(),
+        }]);
+
+        assert_eq!(
+            item,
+            ResponseInputItem::Message {
+                role: "user".to_string(),
+                content: vec![ContentItem::InputText {
+                    text: "Codex does not support local audio input yet.".to_string(),
+                }],
+                phase: None,
+            }
+        );
+
+        Ok(())
+    }
+
     #[test]
     fn image_user_input_preserves_requested_detail() -> Result<()> {
         let image_url = "data:image/png;base64,abc".to_string();
diff --git a/codex-rs/protocol/src/user_input.rs b/codex-rs/protocol/src/user_input.rs
index ce4cf99eba..e8252d6c37 100644
--- a/codex-rs/protocol/src/user_input.rs
+++ b/codex-rs/protocol/src/user_input.rs
@@ -29,7 +29,6 @@ pub enum UserInput {
         #[ts(optional)]
         detail: Option<ImageDetail>,
     },
-
     /// Local image path provided by the user.  This will be converted to an
     /// `Image` variant (base64 data URL) during request serialization.
     LocalImage {
@@ -38,6 +37,10 @@ pub enum UserInput {
         #[ts(optional)]
         detail: Option<ImageDetail>,
     },
+    /// Pre-encoded audio data URI. Audio input is not yet forwarded to the Responses API.
+    Audio { audio_url: String },
+    /// Local audio path provided by the user. Local audio is not converted in this layer.
+    LocalAudio { path: std::path::PathBuf },
 
     /// Skill selected by the user (name + path to SKILL.md).
     Skill {
diff --git a/codex-rs/rollout/src/search.rs b/codex-rs/rollout/src/search.rs
index 805a6b274e..67a2723b49 100644
--- a/codex-rs/rollout/src/search.rs
+++ b/codex-rs/rollout/src/search.rs
@@ -293,7 +293,7 @@ fn conversation_text_from_item(item: &RolloutItem) -> Option<String> {
 fn content_item_text(item: &ContentItem) -> Option<&str> {
     match item {
         ContentItem::InputText { text } | ContentItem::OutputText { text } => Some(text.as_str()),
-        ContentItem::InputImage { .. } => None,
+        ContentItem::InputImage { .. } | ContentItem::InputAudio { .. } => None,
     }
 }
 
diff --git a/codex-rs/tools/src/tool_output.rs b/codex-rs/tools/src/tool_output.rs
index f2eed18fac..7d58b35e89 100644
--- a/codex-rs/tools/src/tool_output.rs
+++ b/codex-rs/tools/src/tool_output.rs
@@ -202,6 +202,9 @@ fn response_input_to_code_mode_result(response: ResponseInputItem) -> JsonValue
                             detail: detail.or(Some(DEFAULT_IMAGE_DETAIL)),
                         }
                     }
+                    codex_protocol::models::ContentItem::InputAudio { audio_url } => {
+                        FunctionCallOutputContentItem::InputAudio { audio_url }
+                    }
                 })
                 .collect::<Vec<_>>(),
         ),
@@ -233,8 +236,14 @@ fn content_items_to_code_mode_result(items: &[FunctionCallOutputContentItem]) ->
                 {
                     Some(image_url.clone())
                 }
+                FunctionCallOutputContentItem::InputAudio { audio_url }
+                    if !audio_url.trim().is_empty() =>
+                {
+                    Some(audio_url.clone())
+                }
                 FunctionCallOutputContentItem::InputText { .. }
                 | FunctionCallOutputContentItem::InputImage { .. }
+                | FunctionCallOutputContentItem::InputAudio { .. }
                 | FunctionCallOutputContentItem::EncryptedContent { .. } => None,
             })
             .collect::<Vec<_>>()
diff --git a/codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__live_app_server_user_message_omits_unsupported_media.snap b/codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__live_app_server_user_message_omits_unsupported_media.snap
new file mode 100644
index 0000000000..6f7384c1b3
--- /dev/null
+++ b/codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__live_app_server_user_message_omits_unsupported_media.snap
@@ -0,0 +1,6 @@
+---
+source: tui/src/chatwidget/tests/app_server.rs
+expression: "lines_to_single_string(&inserted[0])"
+---
+
+› Please inspect the attachments.
diff --git a/codex-rs/tui/src/chatwidget/tests/app_server.rs b/codex-rs/tui/src/chatwidget/tests/app_server.rs
index 4db7692ff3..1181120aaa 100644
--- a/codex-rs/tui/src/chatwidget/tests/app_server.rs
+++ b/codex-rs/tui/src/chatwidget/tests/app_server.rs
@@ -538,6 +538,43 @@ async fn live_app_server_user_message_item_completed_does_not_duplicate_rendered
     assert!(drain_insert_history(&mut rx).is_empty());
 }
 
+#[tokio::test]
+async fn live_app_server_user_message_omits_unsupported_media() {
+    let (mut chat, mut rx, _op_rx) = make_chatwidget_manual(/*model_override*/ None).await;
+
+    chat.handle_server_notification(
+        ServerNotification::ItemCompleted(ItemCompletedNotification {
+            thread_id: "thread-1".to_string(),
+            turn_id: "turn-1".to_string(),
+            completed_at_ms: 0,
+            item: AppServerThreadItem::UserMessage {
+                id: "user-1".to_string(),
+                client_id: None,
+                content: vec![
+                    AppServerUserInput::Text {
+                        text: "Please inspect the attachments.".to_string(),
+                        text_elements: Vec::new(),
+                    },
+                    AppServerUserInput::Audio {
+                        url: "https://example.com/one.wav".to_string(),
+                    },
+                    AppServerUserInput::LocalAudio {
+                        path: test_path_buf("/tmp/two.wav"),
+                    },
+                ],
+            },
+        }),
+        /*replay_kind*/ None,
+    );
+
+    let inserted = drain_insert_history(&mut rx);
+    assert_eq!(inserted.len(), 1);
+    assert_chatwidget_snapshot!(
+        "live_app_server_user_message_omits_unsupported_media",
+        lines_to_single_string(&inserted[0]),
+    );
+}
+
 #[tokio::test]
 async fn live_app_server_turn_completed_clears_working_status_after_answer_item() {
     let (mut chat, mut rx, _op_rx) = make_chatwidget_manual(/*model_override*/ None).await;
diff --git a/codex-rs/tui/src/chatwidget/user_messages.rs b/codex-rs/tui/src/chatwidget/user_messages.rs
index 255ebb6e11..12f0207656 100644
--- a/codex-rs/tui/src/chatwidget/user_messages.rs
+++ b/codex-rs/tui/src/chatwidget/user_messages.rs
@@ -589,7 +589,11 @@ pub(crate) fn mention_bindings_from_user_inputs(
                     path: path.clone(),
                 })
             }
-            UserInput::Text { .. } | UserInput::Image { .. } | UserInput::LocalImage { .. } => None,
+            UserInput::Text { .. }
+            | UserInput::Image { .. }
+            | UserInput::LocalImage { .. }
+            | UserInput::Audio { .. }
+            | UserInput::LocalAudio { .. } => None,
         })
         .collect();
     mention_bindings.sort_by_key(|binding| {
@@ -655,7 +659,10 @@ impl ChatWidget {
             match item {
                 UserInput::Text { text, .. } => message.push_str(text),
                 UserInput::Image { .. } | UserInput::LocalImage { .. } => image_count += 1,
-                UserInput::Skill { .. } | UserInput::Mention { .. } => {}
+                UserInput::Audio { .. }
+                | UserInput::LocalAudio { .. }
+                | UserInput::Skill { .. }
+                | UserInput::Mention { .. } => {}
             }
         }
 
@@ -666,6 +673,12 @@ impl ChatWidget {
     }
 
     pub(crate) fn user_message_display_from_inputs(items: &[UserInput]) -> UserMessageDisplay {
+        if items
+            .iter()
+            .any(|item| matches!(item, UserInput::Audio { .. } | UserInput::LocalAudio { .. }))
+        {
+            tracing::warn!("audio user inputs are not supported by the TUI and will be omitted");
+        }
         let mut message = String::new();
         let mut remote_image_urls = Vec::new();
         let mut local_images = Vec::new();
@@ -694,7 +707,10 @@ impl ChatWidget {
                 ),
                 UserInput::Image { url, .. } => remote_image_urls.push(url.clone()),
                 UserInput::LocalImage { path, .. } => local_images.push(path.clone()),
-                UserInput::Skill { .. } | UserInput::Mention { .. } => {}
+                UserInput::Audio { .. }
+                | UserInput::LocalAudio { .. }
+                | UserInput::Skill { .. }
+                | UserInput::Mention { .. } => {}
             }
         }
 
diff --git a/codex-rs/tui/src/thread_transcript.rs b/codex-rs/tui/src/thread_transcript.rs
index e9b54a7769..b051d3ed2b 100644
--- a/codex-rs/tui/src/thread_transcript.rs
+++ b/codex-rs/tui/src/thread_transcript.rs
@@ -13,6 +13,7 @@ use crate::history_cell::split_reasoning_summary_parts;
 use crate::multi_agents::sub_agent_activity_summary;
 use codex_app_server_protocol::Thread;
 use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::UserInput;
 use codex_protocol::ThreadId;
 use codex_protocol::items::UserMessageItem;
 use ratatui::style::Stylize as _;
@@ -54,6 +55,17 @@ pub(crate) fn thread_to_transcript_cells(
                 client_id,
                 content,
             } => {
+                if content.iter().any(|input| {
+                    matches!(
+                        input,
+                        UserInput::Audio { .. } | UserInput::LocalAudio { .. }
+                    )
+                }) {
+                    tracing::warn!(
+                        user_message_id = id,
+                        "audio user inputs are not supported by the TUI and will be omitted"
+                    );
+                }
                 let item = UserMessageItem {
                     id: id.clone(),
                     client_id: client_id.clone(),
diff --git a/codex-rs/utils/output-truncation/src/lib.rs b/codex-rs/utils/output-truncation/src/lib.rs
index 4fcff7dce4..e2b4a45c88 100644
--- a/codex-rs/utils/output-truncation/src/lib.rs
+++ b/codex-rs/utils/output-truncation/src/lib.rs
@@ -38,12 +38,20 @@ pub fn formatted_truncate_text_content_items_with_policy(
         .filter_map(|item| match item {
             FunctionCallOutputContentItem::InputText { text } => Some(text.as_str()),
             FunctionCallOutputContentItem::InputImage { .. }
+            | FunctionCallOutputContentItem::InputAudio { .. }
             | FunctionCallOutputContentItem::EncryptedContent { .. } => None,
         })
         .collect::<Vec<_>>();
+    let without_audio = || {
+        items
+            .iter()
+            .filter(|item| !matches!(item, FunctionCallOutputContentItem::InputAudio { .. }))
+            .cloned()
+            .collect()
+    };
 
     if text_segments.is_empty() {
-        return (items.to_vec(), None);
+        return (without_audio(), None);
     }
 
     let mut combined = String::new();
@@ -55,7 +63,7 @@ pub fn formatted_truncate_text_content_items_with_policy(
     }
 
     if combined.len() <= policy.byte_budget() {
-        return (items.to_vec(), None);
+        return (without_audio(), None);
     }
 
     let original_token_count = approx_token_count(&combined);
@@ -69,6 +77,7 @@ pub fn formatted_truncate_text_content_items_with_policy(
                 detail: *detail,
             })
         }
+        FunctionCallOutputContentItem::InputAudio { .. } => None,
         FunctionCallOutputContentItem::EncryptedContent { encrypted_content } => {
             Some(FunctionCallOutputContentItem::EncryptedContent {
                 encrypted_content: encrypted_content.clone(),
@@ -127,6 +136,7 @@ pub fn truncate_function_output_items_with_policy(
                     detail: *detail,
                 });
             }
+            FunctionCallOutputContentItem::InputAudio { .. } => {}
             FunctionCallOutputContentItem::EncryptedContent { encrypted_content } => {
                 out.push(FunctionCallOutputContentItem::EncryptedContent {
                     encrypted_content: encrypted_content.clone(),
diff --git a/codex-rs/utils/output-truncation/src/truncate_tests.rs b/codex-rs/utils/output-truncation/src/truncate_tests.rs
index e8907cf8f8..7f8a7cdf60 100644
--- a/codex-rs/utils/output-truncation/src/truncate_tests.rs
+++ b/codex-rs/utils/output-truncation/src/truncate_tests.rs
@@ -208,7 +208,7 @@ fn formatted_truncate_text_content_items_with_policy_preserves_empty_leading_tex
 }
 
 #[test]
-fn formatted_truncate_text_content_items_with_policy_merges_text_and_appends_images() {
+fn formatted_truncate_text_content_items_with_policy_merges_text_and_drops_audio() {
     let items = vec![
         FunctionCallOutputContentItem::InputText {
             text: "abcd".to_string(),
@@ -220,6 +220,9 @@ fn formatted_truncate_text_content_items_with_policy_merges_text_and_appends_ima
         FunctionCallOutputContentItem::InputText {
             text: "efgh".to_string(),
         },
+        FunctionCallOutputContentItem::InputAudio {
+            audio_url: "audio:one".to_string(),
+        },
         FunctionCallOutputContentItem::InputText {
             text: "ijkl".to_string(),
         },
@@ -280,7 +283,7 @@ fn formatted_truncate_text_content_items_with_policy_preserves_encrypted_content
 }
 
 #[test]
-fn truncate_function_output_items_with_policy_preserves_encrypted_content() {
+fn truncate_function_output_items_with_policy_preserves_encrypted_content_and_drops_audio() {
     let items = vec![
         FunctionCallOutputContentItem::InputText {
             text: "abcdefgh".to_string(),
@@ -288,6 +291,9 @@ fn truncate_function_output_items_with_policy_preserves_encrypted_content() {
         FunctionCallOutputContentItem::EncryptedContent {
             encrypted_content: "enc_opaque".to_string(),
         },
+        FunctionCallOutputContentItem::InputAudio {
+            audio_url: "audio:one".to_string(),
+        },
     ];
 
     let output = truncate_function_output_items_with_policy(&items, TruncationPolicy::Bytes(2));