diff --git a/core/http/endpoints/openai/realtime.go b/core/http/endpoints/openai/realtime.go
index 32b08b3fd..8b17a8238 100644
--- a/core/http/endpoints/openai/realtime.go
+++ b/core/http/endpoints/openai/realtime.go
@@ -12,6 +12,7 @@ import (
 	"math"
 	"os"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
 
@@ -1923,7 +1924,7 @@ func commitUtteranceWithTranscript(ctx context.Context, utt []byte, live *liveUt
 	// Generate an LLM response only when there is a transcript to feed it. A
 	// sound-detection-only session (no transcription) has no LLM stage, so it
 	// stops here after emitting the sound-detection event.
-	if session.InputAudioTranscription != nil && !session.TranscriptionOnly {
+	if session.InputAudioTranscription != nil && !session.TranscriptionOnly && strings.TrimSpace(transcript) != "" {
 		generateResponse(ctx, session, utt, transcript, speaker, conv, t)
 	}
 }
diff --git a/core/http/endpoints/openai/realtime_semantic_vad_test.go b/core/http/endpoints/openai/realtime_semantic_vad_test.go
index c3f5d7ef8..c36e13563 100644
--- a/core/http/endpoints/openai/realtime_semantic_vad_test.go
+++ b/core/http/endpoints/openai/realtime_semantic_vad_test.go
@@ -355,6 +355,19 @@ var _ = Describe("commitUtteranceWithTranscript", func() {
 
 		Expect(tr.countEvents(types.ServerEventTypeConversationItemInputAudioTranscriptionCompleted)).To(Equal(1))
 	})
+
+	It("does not generate a response for a blank transcript", func() {
+		session, model := itSession(nil)
+		model.transcribeFinal = &schema.TranscriptionResult{Text: " \t\n"}
+		tr := &fakeTransport{}
+		conv := &Conversation{}
+
+		commitUtterance(context.Background(), []byte{1, 2}, session, conv, tr)
+
+		Expect(tr.countEvents(types.ServerEventTypeConversationItemInputAudioTranscriptionCompleted)).To(Equal(1))
+		Expect(conv.Items).To(BeEmpty())
+		Expect(tr.countEvents(types.ServerEventTypeResponseCreated)).To(Equal(0))
+	})
 })
 
 // transcribeUtterance is the retranscribe gate's offline decode of the