diff --git a/litellm/litellm_core_utils/realtime_streaming.py b/litellm/litellm_core_utils/realtime_streaming.py
index bc2c77e4348..5d7a5bfe318 100644
--- a/litellm/litellm_core_utils/realtime_streaming.py
+++ b/litellm/litellm_core_utils/realtime_streaming.py
@@ -295,9 +295,9 @@ class RealTimeStreaming:
                     safe_msg = str(e) or "I'm sorry, that request was blocked by the content filter."
                 # Cancel any in-flight response before speaking the warning.
                 # This handles the race where create_response fired before we could intercept.
-                await self.backend_ws.send(json.dumps({"type": "response.cancel"}))
-                # Ask OpenAI to speak the warning — TTS audio plays naturally in the client
-                await self.backend_ws.send(
+                await self._send_to_backend(json.dumps({"type": "response.cancel"}))
+                # Ask the model to speak the warning — TTS audio plays naturally in the client
+                await self._send_to_backend(
                     json.dumps(
                         {
                             "type": "response.create",
diff --git a/litellm/llms/gemini/realtime/transformation.py b/litellm/llms/gemini/realtime/transformation.py
index 17a8418bb3c..51c4b9e71e7 100644
--- a/litellm/llms/gemini/realtime/transformation.py
+++ b/litellm/llms/gemini/realtime/transformation.py
@@ -312,13 +312,17 @@ class GeminiRealtimeConfig(BaseRealtimeConfig):
         if _system_instruction is not None and isinstance(_system_instruction, str):
             session["instructions"] = _system_instruction
         if _model is not None and isinstance(_model, str):
-            # Strip "models/" prefix if present to match OpenAI model name format.
-            # Use removeprefix (not strip) — strip removes individual chars, not a substring.
-            session["model"] = (
-                _model[len("models/"):]
-                if _model.startswith("models/")
-                else _model
-            )
+            # Normalise to bare model name for OpenAI compatibility.
+            # Vertex AI uses a full resource path:
+            #   projects/{project}/locations/{location}/publishers/google/models/{model}
+            # Google AI Studio uses:
+            #   models/{model}
+            if "/models/" in _model:
+                session["model"] = _model.split("/models/")[-1]
+            elif _model.startswith("models/"):
+                session["model"] = _model[len("models/"):]
+            else:
+                session["model"] = _model
 
         return OpenAIRealtimeStreamSessionEvents(
             type="session.created",