Add realtime output modality and transcript events (#17701)

- Add outputModality to thread/realtime/start and wire text/audio output
selection through app-server, core, API, and TUI.\n- Rename the realtime
transcript delta notification and add a separate transcript done
notification that forwards final text from item done without correlating
it with deltas.

codex-rs/app-server-protocol/schema/json/ClientRequest.json

@@ -1525,6 +1525,13 @@
         }
       ]
     },
+    "RealtimeOutputModality": {
+      "enum": [
+        "text",
+        "audio"
+      ],
+      "type": "string"
+    },
     "RealtimeVoice": {
       "enum": [
         "alloy",

codex-rs/app-server-protocol/schema/json/ServerNotification.json

@@ -3384,13 +3384,35 @@
       ],
       "type": "object"
     },
-    "ThreadRealtimeTranscriptUpdatedNotification": {
+    "ThreadRealtimeTranscriptDeltaNotification": {
       "description": "EXPERIMENTAL - flat transcript delta emitted whenever realtime transcript text changes.",
+      "properties": {
+        "delta": {
+          "description": "Live transcript delta from the realtime event.",
+          "type": "string"
+        },
+        "role": {
+          "type": "string"
+        },
+        "threadId": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "delta",
+        "role",
+        "threadId"
+      ],
+      "type": "object"
+    },
+    "ThreadRealtimeTranscriptDoneNotification": {
+      "description": "EXPERIMENTAL - final transcript text emitted when realtime completes a transcript part.",
       "properties": {
         "role": {
           "type": "string"
         },
         "text": {
+          "description": "Final complete text for the transcript part.",
           "type": "string"
         },
         "threadId": {
@@ -4949,20 +4971,40 @@
       "properties": {
         "method": {
           "enum": [
-            "thread/realtime/transcriptUpdated"
+            "thread/realtime/transcript/delta"
           ],
-          "title": "Thread/realtime/transcriptUpdatedNotificationMethod",
+          "title": "Thread/realtime/transcript/deltaNotificationMethod",
           "type": "string"
         },
         "params": {
-          "$ref": "#/definitions/ThreadRealtimeTranscriptUpdatedNotification"
+          "$ref": "#/definitions/ThreadRealtimeTranscriptDeltaNotification"
         }
       },
       "required": [
         "method",
         "params"
       ],
-      "title": "Thread/realtime/transcriptUpdatedNotification",
+      "title": "Thread/realtime/transcript/deltaNotification",
+      "type": "object"
+    },
+    {
+      "properties": {
+        "method": {
+          "enum": [
+            "thread/realtime/transcript/done"
+          ],
+          "title": "Thread/realtime/transcript/doneNotificationMethod",
+          "type": "string"
+        },
+        "params": {
+          "$ref": "#/definitions/ThreadRealtimeTranscriptDoneNotification"
+        }
+      },
+      "required": [
+        "method",
+        "params"
+      ],
+      "title": "Thread/realtime/transcript/doneNotification",
       "type": "object"
     },
     {

codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json

@@ -4379,20 +4379,40 @@
           "properties": {
             "method": {
               "enum": [
-                "thread/realtime/transcriptUpdated"
+                "thread/realtime/transcript/delta"
               ],
-              "title": "Thread/realtime/transcriptUpdatedNotificationMethod",
+              "title": "Thread/realtime/transcript/deltaNotificationMethod",
               "type": "string"
             },
             "params": {
-              "$ref": "#/definitions/v2/ThreadRealtimeTranscriptUpdatedNotification"
+              "$ref": "#/definitions/v2/ThreadRealtimeTranscriptDeltaNotification"
             }
           },
           "required": [
             "method",
             "params"
           ],
-          "title": "Thread/realtime/transcriptUpdatedNotification",
+          "title": "Thread/realtime/transcript/deltaNotification",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "method": {
+              "enum": [
+                "thread/realtime/transcript/done"
+              ],
+              "title": "Thread/realtime/transcript/doneNotificationMethod",
+              "type": "string"
+            },
+            "params": {
+              "$ref": "#/definitions/v2/ThreadRealtimeTranscriptDoneNotification"
+            }
+          },
+          "required": [
+            "method",
+            "params"
+          ],
+          "title": "Thread/realtime/transcript/doneNotification",
           "type": "object"
         },
         {
@@ -10718,6 +10738,13 @@
         ],
         "type": "string"
       },
+      "RealtimeOutputModality": {
+        "enum": [
+          "text",
+          "audio"
+        ],
+        "type": "string"
+      },
       "RealtimeVoice": {
         "enum": [
           "alloy",
@@ -14088,14 +14115,38 @@
         "title": "ThreadRealtimeStartedNotification",
         "type": "object"
       },
-      "ThreadRealtimeTranscriptUpdatedNotification": {
+      "ThreadRealtimeTranscriptDeltaNotification": {
         "$schema": "http://json-schema.org/draft-07/schema#",
         "description": "EXPERIMENTAL - flat transcript delta emitted whenever realtime transcript text changes.",
+        "properties": {
+          "delta": {
+            "description": "Live transcript delta from the realtime event.",
+            "type": "string"
+          },
+          "role": {
+            "type": "string"
+          },
+          "threadId": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "delta",
+          "role",
+          "threadId"
+        ],
+        "title": "ThreadRealtimeTranscriptDeltaNotification",
+        "type": "object"
+      },
+      "ThreadRealtimeTranscriptDoneNotification": {
+        "$schema": "http://json-schema.org/draft-07/schema#",
+        "description": "EXPERIMENTAL - final transcript text emitted when realtime completes a transcript part.",
         "properties": {
           "role": {
             "type": "string"
           },
           "text": {
+            "description": "Final complete text for the transcript part.",
             "type": "string"
           },
           "threadId": {
@@ -14107,7 +14158,7 @@
           "text",
           "threadId"
         ],
-        "title": "ThreadRealtimeTranscriptUpdatedNotification",
+        "title": "ThreadRealtimeTranscriptDoneNotification",
         "type": "object"
       },
       "ThreadResumeParams": {

codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json

@@ -7514,6 +7514,13 @@
       ],
       "type": "string"
     },
+    "RealtimeOutputModality": {
+      "enum": [
+        "text",
+        "audio"
+      ],
+      "type": "string"
+    },
     "RealtimeVoice": {
       "enum": [
         "alloy",
@@ -9683,20 +9690,40 @@
           "properties": {
             "method": {
               "enum": [
-                "thread/realtime/transcriptUpdated"
+                "thread/realtime/transcript/delta"
               ],
-              "title": "Thread/realtime/transcriptUpdatedNotificationMethod",
+              "title": "Thread/realtime/transcript/deltaNotificationMethod",
               "type": "string"
             },
             "params": {
-              "$ref": "#/definitions/ThreadRealtimeTranscriptUpdatedNotification"
+              "$ref": "#/definitions/ThreadRealtimeTranscriptDeltaNotification"
             }
           },
           "required": [
             "method",
             "params"
           ],
-          "title": "Thread/realtime/transcriptUpdatedNotification",
+          "title": "Thread/realtime/transcript/deltaNotification",
+          "type": "object"
+        },
+        {
+          "properties": {
+            "method": {
+              "enum": [
+                "thread/realtime/transcript/done"
+              ],
+              "title": "Thread/realtime/transcript/doneNotificationMethod",
+              "type": "string"
+            },
+            "params": {
+              "$ref": "#/definitions/ThreadRealtimeTranscriptDoneNotification"
+            }
+          },
+          "required": [
+            "method",
+            "params"
+          ],
+          "title": "Thread/realtime/transcript/doneNotification",
           "type": "object"
         },
         {
@@ -11936,14 +11963,38 @@
       "title": "ThreadRealtimeStartedNotification",
       "type": "object"
     },
-    "ThreadRealtimeTranscriptUpdatedNotification": {
+    "ThreadRealtimeTranscriptDeltaNotification": {
       "$schema": "http://json-schema.org/draft-07/schema#",
       "description": "EXPERIMENTAL - flat transcript delta emitted whenever realtime transcript text changes.",
+      "properties": {
+        "delta": {
+          "description": "Live transcript delta from the realtime event.",
+          "type": "string"
+        },
+        "role": {
+          "type": "string"
+        },
+        "threadId": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "delta",
+        "role",
+        "threadId"
+      ],
+      "title": "ThreadRealtimeTranscriptDeltaNotification",
+      "type": "object"
+    },
+    "ThreadRealtimeTranscriptDoneNotification": {
+      "$schema": "http://json-schema.org/draft-07/schema#",
+      "description": "EXPERIMENTAL - final transcript text emitted when realtime completes a transcript part.",
       "properties": {
         "role": {
           "type": "string"
         },
         "text": {
+          "description": "Final complete text for the transcript part.",
           "type": "string"
         },
         "threadId": {
@@ -11955,7 +12006,7 @@
         "text",
         "threadId"
       ],
-      "title": "ThreadRealtimeTranscriptUpdatedNotification",
+      "title": "ThreadRealtimeTranscriptDoneNotification",
       "type": "object"
     },
     "ThreadResumeParams": {

codex-rs/app-server-protocol/schema/json/v2/ThreadRealtimeTranscriptDeltaNotification.json

@@ -2,10 +2,11 @@
   "$schema": "http://json-schema.org/draft-07/schema#",
   "description": "EXPERIMENTAL - flat transcript delta emitted whenever realtime transcript text changes.",
   "properties": {
-    "role": {
+    "delta": {
+      "description": "Live transcript delta from the realtime event.",
       "type": "string"
     },
-    "text": {
+    "role": {
       "type": "string"
     },
     "threadId": {
@@ -13,10 +14,10 @@
     }
   },
   "required": [
+    "delta",
     "role",
-    "text",
     "threadId"
   ],
-  "title": "ThreadRealtimeTranscriptUpdatedNotification",
+  "title": "ThreadRealtimeTranscriptDeltaNotification",
   "type": "object"
 }

codex-rs/app-server-protocol/schema/json/v2/ThreadRealtimeTranscriptDoneNotification.json

@@ -0,0 +1,23 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "description": "EXPERIMENTAL - final transcript text emitted when realtime completes a transcript part.",
+  "properties": {
+    "role": {
+      "type": "string"
+    },
+    "text": {
+      "description": "Final complete text for the transcript part.",
+      "type": "string"
+    },
+    "threadId": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "role",
+    "text",
+    "threadId"
+  ],
+  "title": "ThreadRealtimeTranscriptDoneNotification",
+  "type": "object"
+}

codex-rs/app-server-protocol/schema/typescript/RealtimeOutputModality.ts

@@ -0,0 +1,5 @@
+// GENERATED CODE! DO NOT MODIFY BY HAND!
+
+// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
+
+export type RealtimeOutputModality = "text" | "audio";

codex-rs/app-server-protocol/schema/typescript/ServerNotification.ts

@@ -43,7 +43,8 @@ import type { ThreadRealtimeItemAddedNotification } from "./v2/ThreadRealtimeIte
 import type { ThreadRealtimeOutputAudioDeltaNotification } from "./v2/ThreadRealtimeOutputAudioDeltaNotification";
 import type { ThreadRealtimeSdpNotification } from "./v2/ThreadRealtimeSdpNotification";
 import type { ThreadRealtimeStartedNotification } from "./v2/ThreadRealtimeStartedNotification";
-import type { ThreadRealtimeTranscriptUpdatedNotification } from "./v2/ThreadRealtimeTranscriptUpdatedNotification";
+import type { ThreadRealtimeTranscriptDeltaNotification } from "./v2/ThreadRealtimeTranscriptDeltaNotification";
+import type { ThreadRealtimeTranscriptDoneNotification } from "./v2/ThreadRealtimeTranscriptDoneNotification";
 import type { ThreadStartedNotification } from "./v2/ThreadStartedNotification";
 import type { ThreadStatusChangedNotification } from "./v2/ThreadStatusChangedNotification";
 import type { ThreadTokenUsageUpdatedNotification } from "./v2/ThreadTokenUsageUpdatedNotification";
@@ -58,4 +59,4 @@ import type { WindowsWorldWritableWarningNotification } from "./v2/WindowsWorldW
 /**
  * Notification sent from the server to the client.
  */
-export type ServerNotification = { "method": "error", "params": ErrorNotification } | { "method": "thread/started", "params": ThreadStartedNotification } | { "method": "thread/status/changed", "params": ThreadStatusChangedNotification } | { "method": "thread/archived", "params": ThreadArchivedNotification } | { "method": "thread/unarchived", "params": ThreadUnarchivedNotification } | { "method": "thread/closed", "params": ThreadClosedNotification } | { "method": "skills/changed", "params": SkillsChangedNotification } | { "method": "thread/name/updated", "params": ThreadNameUpdatedNotification } | { "method": "thread/tokenUsage/updated", "params": ThreadTokenUsageUpdatedNotification } | { "method": "turn/started", "params": TurnStartedNotification } | { "method": "hook/started", "params": HookStartedNotification } | { "method": "turn/completed", "params": TurnCompletedNotification } | { "method": "hook/completed", "params": HookCompletedNotification } | { "method": "turn/diff/updated", "params": TurnDiffUpdatedNotification } | { "method": "turn/plan/updated", "params": TurnPlanUpdatedNotification } | { "method": "item/started", "params": ItemStartedNotification } | { "method": "item/autoApprovalReview/started", "params": ItemGuardianApprovalReviewStartedNotification } | { "method": "item/autoApprovalReview/completed", "params": ItemGuardianApprovalReviewCompletedNotification } | { "method": "item/completed", "params": ItemCompletedNotification } | { "method": "rawResponseItem/completed", "params": RawResponseItemCompletedNotification } | { "method": "item/agentMessage/delta", "params": AgentMessageDeltaNotification } | { "method": "item/plan/delta", "params": PlanDeltaNotification } | { "method": "command/exec/outputDelta", "params": CommandExecOutputDeltaNotification } | { "method": "item/commandExecution/outputDelta", "params": CommandExecutionOutputDeltaNotification } | { "method": "item/commandExecution/terminalInteraction", "params": TerminalInteractionNotification } | { "method": "item/fileChange/outputDelta", "params": FileChangeOutputDeltaNotification } | { "method": "serverRequest/resolved", "params": ServerRequestResolvedNotification } | { "method": "item/mcpToolCall/progress", "params": McpToolCallProgressNotification } | { "method": "mcpServer/oauthLogin/completed", "params": McpServerOauthLoginCompletedNotification } | { "method": "mcpServer/startupStatus/updated", "params": McpServerStatusUpdatedNotification } | { "method": "account/updated", "params": AccountUpdatedNotification } | { "method": "account/rateLimits/updated", "params": AccountRateLimitsUpdatedNotification } | { "method": "app/list/updated", "params": AppListUpdatedNotification } | { "method": "fs/changed", "params": FsChangedNotification } | { "method": "item/reasoning/summaryTextDelta", "params": ReasoningSummaryTextDeltaNotification } | { "method": "item/reasoning/summaryPartAdded", "params": ReasoningSummaryPartAddedNotification } | { "method": "item/reasoning/textDelta", "params": ReasoningTextDeltaNotification } | { "method": "thread/compacted", "params": ContextCompactedNotification } | { "method": "model/rerouted", "params": ModelReroutedNotification } | { "method": "deprecationNotice", "params": DeprecationNoticeNotification } | { "method": "configWarning", "params": ConfigWarningNotification } | { "method": "fuzzyFileSearch/sessionUpdated", "params": FuzzyFileSearchSessionUpdatedNotification } | { "method": "fuzzyFileSearch/sessionCompleted", "params": FuzzyFileSearchSessionCompletedNotification } | { "method": "thread/realtime/started", "params": ThreadRealtimeStartedNotification } | { "method": "thread/realtime/itemAdded", "params": ThreadRealtimeItemAddedNotification } | { "method": "thread/realtime/transcriptUpdated", "params": ThreadRealtimeTranscriptUpdatedNotification } | { "method": "thread/realtime/outputAudio/delta", "params": ThreadRealtimeOutputAudioDeltaNotification } | { "method": "thread/realtime/sdp", "params": ThreadRealtimeSdpNotification } | { "method": "thread/realtime/error", "params": ThreadRealtimeErrorNotification } | { "method": "thread/realtime/closed", "params": ThreadRealtimeClosedNotification } | { "method": "windows/worldWritableWarning", "params": WindowsWorldWritableWarningNotification } | { "method": "windowsSandbox/setupCompleted", "params": WindowsSandboxSetupCompletedNotification } | { "method": "account/login/completed", "params": AccountLoginCompletedNotification };
+export type ServerNotification = { "method": "error", "params": ErrorNotification } | { "method": "thread/started", "params": ThreadStartedNotification } | { "method": "thread/status/changed", "params": ThreadStatusChangedNotification } | { "method": "thread/archived", "params": ThreadArchivedNotification } | { "method": "thread/unarchived", "params": ThreadUnarchivedNotification } | { "method": "thread/closed", "params": ThreadClosedNotification } | { "method": "skills/changed", "params": SkillsChangedNotification } | { "method": "thread/name/updated", "params": ThreadNameUpdatedNotification } | { "method": "thread/tokenUsage/updated", "params": ThreadTokenUsageUpdatedNotification } | { "method": "turn/started", "params": TurnStartedNotification } | { "method": "hook/started", "params": HookStartedNotification } | { "method": "turn/completed", "params": TurnCompletedNotification } | { "method": "hook/completed", "params": HookCompletedNotification } | { "method": "turn/diff/updated", "params": TurnDiffUpdatedNotification } | { "method": "turn/plan/updated", "params": TurnPlanUpdatedNotification } | { "method": "item/started", "params": ItemStartedNotification } | { "method": "item/autoApprovalReview/started", "params": ItemGuardianApprovalReviewStartedNotification } | { "method": "item/autoApprovalReview/completed", "params": ItemGuardianApprovalReviewCompletedNotification } | { "method": "item/completed", "params": ItemCompletedNotification } | { "method": "rawResponseItem/completed", "params": RawResponseItemCompletedNotification } | { "method": "item/agentMessage/delta", "params": AgentMessageDeltaNotification } | { "method": "item/plan/delta", "params": PlanDeltaNotification } | { "method": "command/exec/outputDelta", "params": CommandExecOutputDeltaNotification } | { "method": "item/commandExecution/outputDelta", "params": CommandExecutionOutputDeltaNotification } | { "method": "item/commandExecution/terminalInteraction", "params": TerminalInteractionNotification } | { "method": "item/fileChange/outputDelta", "params": FileChangeOutputDeltaNotification } | { "method": "serverRequest/resolved", "params": ServerRequestResolvedNotification } | { "method": "item/mcpToolCall/progress", "params": McpToolCallProgressNotification } | { "method": "mcpServer/oauthLogin/completed", "params": McpServerOauthLoginCompletedNotification } | { "method": "mcpServer/startupStatus/updated", "params": McpServerStatusUpdatedNotification } | { "method": "account/updated", "params": AccountUpdatedNotification } | { "method": "account/rateLimits/updated", "params": AccountRateLimitsUpdatedNotification } | { "method": "app/list/updated", "params": AppListUpdatedNotification } | { "method": "fs/changed", "params": FsChangedNotification } | { "method": "item/reasoning/summaryTextDelta", "params": ReasoningSummaryTextDeltaNotification } | { "method": "item/reasoning/summaryPartAdded", "params": ReasoningSummaryPartAddedNotification } | { "method": "item/reasoning/textDelta", "params": ReasoningTextDeltaNotification } | { "method": "thread/compacted", "params": ContextCompactedNotification } | { "method": "model/rerouted", "params": ModelReroutedNotification } | { "method": "deprecationNotice", "params": DeprecationNoticeNotification } | { "method": "configWarning", "params": ConfigWarningNotification } | { "method": "fuzzyFileSearch/sessionUpdated", "params": FuzzyFileSearchSessionUpdatedNotification } | { "method": "fuzzyFileSearch/sessionCompleted", "params": FuzzyFileSearchSessionCompletedNotification } | { "method": "thread/realtime/started", "params": ThreadRealtimeStartedNotification } | { "method": "thread/realtime/itemAdded", "params": ThreadRealtimeItemAddedNotification } | { "method": "thread/realtime/transcript/delta", "params": ThreadRealtimeTranscriptDeltaNotification } | { "method": "thread/realtime/transcript/done", "params": ThreadRealtimeTranscriptDoneNotification } | { "method": "thread/realtime/outputAudio/delta", "params": ThreadRealtimeOutputAudioDeltaNotification } | { "method": "thread/realtime/sdp", "params": ThreadRealtimeSdpNotification } | { "method": "thread/realtime/error", "params": ThreadRealtimeErrorNotification } | { "method": "thread/realtime/closed", "params": ThreadRealtimeClosedNotification } | { "method": "windows/worldWritableWarning", "params": WindowsWorldWritableWarningNotification } | { "method": "windowsSandbox/setupCompleted", "params": WindowsSandboxSetupCompletedNotification } | { "method": "account/login/completed", "params": AccountLoginCompletedNotification };

codex-rs/app-server-protocol/schema/typescript/index.ts

@@ -49,6 +49,7 @@ export type { ParsedCommand } from "./ParsedCommand";
 export type { Personality } from "./Personality";
 export type { PlanType } from "./PlanType";
 export type { RealtimeConversationVersion } from "./RealtimeConversationVersion";
+export type { RealtimeOutputModality } from "./RealtimeOutputModality";
 export type { RealtimeVoice } from "./RealtimeVoice";
 export type { RealtimeVoicesList } from "./RealtimeVoicesList";
 export type { ReasoningEffort } from "./ReasoningEffort";

codex-rs/app-server-protocol/schema/typescript/v2/ThreadRealtimeTranscriptDeltaNotification.ts

@@ -6,4 +6,8 @@
  * EXPERIMENTAL - flat transcript delta emitted whenever realtime
  * transcript text changes.
  */
-export type ThreadRealtimeTranscriptUpdatedNotification = { threadId: string, role: string, text: string, };
+export type ThreadRealtimeTranscriptDeltaNotification = { threadId: string, role: string,
+/**
+ * Live transcript delta from the realtime event.
+ */
+delta: string, };

codex-rs/app-server-protocol/schema/typescript/v2/ThreadRealtimeTranscriptDoneNotification.ts

@@ -0,0 +1,13 @@
+// GENERATED CODE! DO NOT MODIFY BY HAND!
+
+// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
+
+/**
+ * EXPERIMENTAL - final transcript text emitted when realtime completes
+ * a transcript part.
+ */
+export type ThreadRealtimeTranscriptDoneNotification = { threadId: string, role: string,
+/**
+ * Final complete text for the transcript part.
+ */
+text: string, };

codex-rs/app-server-protocol/schema/typescript/v2/index.ts

@@ -305,7 +305,8 @@ export type { ThreadRealtimeOutputAudioDeltaNotification } from "./ThreadRealtim
 export type { ThreadRealtimeSdpNotification } from "./ThreadRealtimeSdpNotification";
 export type { ThreadRealtimeStartTransport } from "./ThreadRealtimeStartTransport";
 export type { ThreadRealtimeStartedNotification } from "./ThreadRealtimeStartedNotification";
-export type { ThreadRealtimeTranscriptUpdatedNotification } from "./ThreadRealtimeTranscriptUpdatedNotification";
+export type { ThreadRealtimeTranscriptDeltaNotification } from "./ThreadRealtimeTranscriptDeltaNotification";
+export type { ThreadRealtimeTranscriptDoneNotification } from "./ThreadRealtimeTranscriptDoneNotification";
 export type { ThreadResumeParams } from "./ThreadResumeParams";
 export type { ThreadResumeResponse } from "./ThreadResumeResponse";
 export type { ThreadRollbackParams } from "./ThreadRollbackParams";

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -1026,8 +1026,10 @@ server_notification_definitions! {
     ThreadRealtimeStarted => "thread/realtime/started" (v2::ThreadRealtimeStartedNotification),
     #[experimental("thread/realtime/itemAdded")]
     ThreadRealtimeItemAdded => "thread/realtime/itemAdded" (v2::ThreadRealtimeItemAddedNotification),
-    #[experimental("thread/realtime/transcriptUpdated")]
-    ThreadRealtimeTranscriptUpdated => "thread/realtime/transcriptUpdated" (v2::ThreadRealtimeTranscriptUpdatedNotification),
+    #[experimental("thread/realtime/transcript/delta")]
+    ThreadRealtimeTranscriptDelta => "thread/realtime/transcript/delta" (v2::ThreadRealtimeTranscriptDeltaNotification),
+    #[experimental("thread/realtime/transcript/done")]
+    ThreadRealtimeTranscriptDone => "thread/realtime/transcript/done" (v2::ThreadRealtimeTranscriptDoneNotification),
     #[experimental("thread/realtime/outputAudio/delta")]
     ThreadRealtimeOutputAudioDelta => "thread/realtime/outputAudio/delta" (v2::ThreadRealtimeOutputAudioDeltaNotification),
     #[experimental("thread/realtime/sdp")]
@@ -1060,6 +1062,8 @@ mod tests {
     use codex_protocol::account::PlanType;
     use codex_protocol::parse_command::ParsedCommand;
     use codex_protocol::protocol::RealtimeConversationVersion;
+    use codex_protocol::protocol::RealtimeOutputModality;
+    use codex_protocol::protocol::RealtimeVoice;
     use codex_utils_absolute_path::AbsolutePathBuf;
     use pretty_assertions::assert_eq;
     use serde_json::json;
@@ -1788,10 +1792,11 @@ mod tests {
             request_id: RequestId::Integer(9),
             params: v2::ThreadRealtimeStartParams {
                 thread_id: "thr_123".to_string(),
+                output_modality: RealtimeOutputModality::Audio,
                 prompt: Some(Some("You are on a call".to_string())),
                 session_id: Some("sess_456".to_string()),
                 transport: None,
-                voice: Some(codex_protocol::protocol::RealtimeVoice::Marin),
+                voice: Some(RealtimeVoice::Marin),
             },
         };
         assert_eq!(
@@ -1800,6 +1805,7 @@ mod tests {
                 "id": 9,
                 "params": {
                     "threadId": "thr_123",
+                    "outputModality": "audio",
                     "prompt": "You are on a call",
                     "sessionId": "sess_456",
                     "transport": null,
@@ -1817,6 +1823,7 @@ mod tests {
             request_id: RequestId::Integer(9),
             params: v2::ThreadRealtimeStartParams {
                 thread_id: "thr_123".to_string(),
+                output_modality: RealtimeOutputModality::Audio,
                 prompt: None,
                 session_id: None,
                 transport: None,
@@ -1829,6 +1836,7 @@ mod tests {
                 "id": 9,
                 "params": {
                     "threadId": "thr_123",
+                    "outputModality": "audio",
                     "sessionId": null,
                     "transport": null,
                     "voice": null
@@ -1841,6 +1849,7 @@ mod tests {
             request_id: RequestId::Integer(9),
             params: v2::ThreadRealtimeStartParams {
                 thread_id: "thr_123".to_string(),
+                output_modality: RealtimeOutputModality::Audio,
                 prompt: Some(None),
                 session_id: None,
                 transport: None,
@@ -1853,6 +1862,7 @@ mod tests {
                 "id": 9,
                 "params": {
                     "threadId": "thr_123",
+                    "outputModality": "audio",
                     "prompt": null,
                     "sessionId": null,
                     "transport": null,
@@ -1867,6 +1877,7 @@ mod tests {
             "id": 9,
             "params": {
                 "threadId": "thr_123",
+                "outputModality": "audio",
                 "sessionId": null,
                 "transport": null,
                 "voice": null
@@ -1882,6 +1893,7 @@ mod tests {
             "id": 9,
             "params": {
                 "threadId": "thr_123",
+                "outputModality": "audio",
                 "prompt": null,
                 "sessionId": null,
                 "transport": null,
@@ -1966,6 +1978,7 @@ mod tests {
             request_id: RequestId::Integer(1),
             params: v2::ThreadRealtimeStartParams {
                 thread_id: "thr_123".to_string(),
+                output_modality: RealtimeOutputModality::Audio,
                 prompt: Some(Some("You are on a call".to_string())),
                 session_id: None,
                 transport: None,

codex-rs/app-server-protocol/src/protocol/v2.rs

@@ -74,6 +74,7 @@ use codex_protocol::protocol::RateLimitWindow as CoreRateLimitWindow;
 use codex_protocol::protocol::ReadOnlyAccess as CoreReadOnlyAccess;
 use codex_protocol::protocol::RealtimeAudioFrame as CoreRealtimeAudioFrame;
 use codex_protocol::protocol::RealtimeConversationVersion;
+use codex_protocol::protocol::RealtimeOutputModality;
 use codex_protocol::protocol::RealtimeVoice;
 use codex_protocol::protocol::RealtimeVoicesList;
 use codex_protocol::protocol::ReviewDecision as CoreReviewDecision;
@@ -3976,11 +3977,14 @@ impl From<ThreadRealtimeAudioChunk> for CoreRealtimeAudioFrame {
 }
 
 /// EXPERIMENTAL - start a thread-scoped realtime session.
-#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, JsonSchema, TS)]
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]
 pub struct ThreadRealtimeStartParams {
     pub thread_id: String,
+    /// Selects text or audio output for the realtime session. Transport and voice stay
+    /// independent so clients can choose how they connect separately from what the model emits.
+    pub output_modality: RealtimeOutputModality,
     #[serde(
         default,
         deserialize_with = "super::serde_helpers::deserialize_double_option",
@@ -4098,9 +4102,22 @@ pub struct ThreadRealtimeItemAddedNotification {
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]
-pub struct ThreadRealtimeTranscriptUpdatedNotification {
+pub struct ThreadRealtimeTranscriptDeltaNotification {
     pub thread_id: String,
     pub role: String,
+    /// Live transcript delta from the realtime event.
+    pub delta: String,
+}
+
+/// EXPERIMENTAL - final transcript text emitted when realtime completes
+/// a transcript part.
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct ThreadRealtimeTranscriptDoneNotification {
+    pub thread_id: String,
+    pub role: String,
+    /// Final complete text for the transcript part.
     pub text: String,
 }