diff --git a/litellm/types/llms/openai.py b/litellm/types/llms/openai.py
index 51e408f8c6..0c854d89bb 100644
--- a/litellm/types/llms/openai.py
+++ b/litellm/types/llms/openai.py
@@ -1892,7 +1892,7 @@ class OpenAIRealtimeStreamResponseOutputItemContent(TypedDict, total=False):
     """The ID of the previous conversation item for reference"""
     text: str
     """The text content, used for 'input_text' / 'text' / 'output_text' content types"""
-    transcript: str
+    transcript: Optional[str]
     """The transcript content, used for 'input_audio' / 'audio' content types"""
     type: Literal[
         "input_audio",
@@ -1998,7 +1998,7 @@ class OpenAIRealtimeResponseContentPart(TypedDict, total=False):
     text: str
     """The text content, if type is 'text' or 'output_text'"""
 
-    transcript: str
+    transcript: Optional[str]
     """The transcript content, if type is 'audio' or 'output_audio'"""
 
     type: Union[
diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py
index d973f8b454..3d45a3409d 100644
--- a/tests/test_litellm/test_cost_calculator.py
+++ b/tests/test_litellm/test_cost_calculator.py
@@ -12,6 +12,7 @@ from pydantic import BaseModel
 
 import litellm
 from litellm.cost_calculator import (
+    RealtimeAPITokenUsageProcessor,
     completion_cost,
     cost_per_token,
     handle_realtime_stream_cost_calculation,
@@ -385,6 +386,43 @@ def test_handle_realtime_stream_cost_calculation():
     assert cost == 0.0  # No usage, no cost
 
 
+def test_realtime_logging_object_allows_null_transcript_in_conversation_item_added():
+    results: OpenAIRealtimeStreamList = [
+        {
+            "type": "conversation.item.added",
+            "event_id": "event_added",
+            "item": {
+                "id": "item_123",
+                "type": "message",
+                "role": "assistant",
+                "status": "in_progress",
+                "content": [{"type": "audio", "transcript": None}],
+            },
+        },
+        {
+            "type": "response.done",
+            "event_id": "event_done",
+            "response": {
+                "id": "resp_123",
+                "object": "realtime.response",
+                "status": "completed",
+                "usage": {"input_tokens": 11, "output_tokens": 7, "total_tokens": 18},
+            },
+        },
+    ]
+
+    usage = RealtimeAPITokenUsageProcessor.collect_and_combine_usage_from_realtime_stream_results(
+        results=results
+    )
+    logging_result = RealtimeAPITokenUsageProcessor.create_logging_realtime_object(
+        usage=usage,
+        results=results,
+    )
+
+    assert logging_result.usage.total_tokens == 18
+    assert logging_result.results[0]["item"]["content"][0]["transcript"] is None
+
+
 def test_custom_pricing_with_router_model_id():
     from litellm import Router