diff --git a/docs/speech-to-text/realtime/turn-detection.mdx b/docs/speech-to-text/realtime/turn-detection.mdx
index 396993e9..d96fcf44 100644
--- a/docs/speech-to-text/realtime/turn-detection.mdx
+++ b/docs/speech-to-text/realtime/turn-detection.mdx
@@ -120,7 +120,7 @@ You can also use `ForceEndOfUtterance` with multi-channel diarization:
 }
 ```
 
-When this message is received, the server will send an [AddTranscript](../../api-ref/realtime-transcription-websocket#addtranscript) message, followed by an [EndOfUtterance](../../api-ref/realtime-transcription-websocket#endofutterance) message.
+When this message is received, the server will send an [AddTranscript](../../api-ref/realtime-transcription-websocket#addtranscript) message, with a `forced` field to indicate it came from a ForceEndOfUtterance request, followed by an [EndOfUtterance](../../api-ref/realtime-transcription-websocket#endofutterance) message..
 
 ## Semantic turn detection
 
diff --git a/spec/realtime.yaml b/spec/realtime.yaml
index 58be4291..424d8406 100644
--- a/spec/realtime.yaml
+++ b/spec/realtime.yaml
@@ -483,6 +483,10 @@ components:
           type: string
           description: |
             The channel identifier to which the audio belongs. This field is only seen in multichannel.
+        forced:
+          type: boolean
+          description: |
+            Indicates whether this message was triggered as a result of a ForceEndOfUtterance request.     
       required:
         - message
         - metadata
@@ -506,6 +510,10 @@ components:
           type: string
           description: |
             The channel identifier to which the audio belongs. This field is only seen in multichannel.
+        forced:
+          type: boolean
+          description: |
+            Indicates whether this message was triggered as a result of a ForceEndOfUtterance request.      
       required:
         - message
         - metadata