diff --git a/litellm/llms/gemini/realtime/transformation.py b/litellm/llms/gemini/realtime/transformation.py
index aa99cc3695f..689f229e393 100644
--- a/litellm/llms/gemini/realtime/transformation.py
+++ b/litellm/llms/gemini/realtime/transformation.py
@@ -904,7 +904,7 @@ class GeminiRealtimeConfig(BaseRealtimeConfig):
         )
         temperature = generation_config.get("temperature")
         max_output_tokens = generation_config.get("max_output_tokens")
-        gemini_modalities = generation_config.get("responseModalities", ["TEXT"])
+        gemini_modalities = generation_config.get("responseModalities", ["AUDIO"])
         _modalities = [
             modality.lower() for modality in cast(List[str], gemini_modalities)
         ]
diff --git a/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py b/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
index c95a085d17c..0e619a50872 100644
--- a/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
+++ b/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
@@ -265,9 +265,9 @@ def test_gemini_realtime_transformation_generation_complete():
     contains_audio_done_event = False
     for response in responses:
         if response["type"] == OpenAIRealtimeEventTypes.RESPONSE_AUDIO_DONE.value:
-            contains_audio_delta = True
+            contains_audio_done_event = True
             break
-    assert contains_audio_delta, "Expected audio delta event"
+    assert contains_audio_done_event, "Expected audio done event"
 
 
 def test_gemini_3_1_flash_live_preview_model_cost_map_entry():