From bfc0c84930938c87d5f64b09c54f68e889c0d6d0 Mon Sep 17 00:00:00 2001
From: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
Date: Thu, 26 Feb 2026 01:08:02 -0800
Subject: [PATCH] fix(vertex_ai): enable inputAudioTranscription in realtime
 session config

Add inputAudioTranscription to the Vertex AI realtime setup so the backend returns transcripts of user speech, allowing guardrails to inspect voice input.

Made-with: Cursor
---
 litellm/llms/vertex_ai/realtime/transformation.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/litellm/llms/vertex_ai/realtime/transformation.py b/litellm/llms/vertex_ai/realtime/transformation.py
index eaa9844f108..5eae143175b 100644
--- a/litellm/llms/vertex_ai/realtime/transformation.py
+++ b/litellm/llms/vertex_ai/realtime/transformation.py
@@ -124,6 +124,8 @@ class VertexAIRealtimeConfig(GeminiRealtimeConfig):
                     "silenceDurationMs": 800,
                 }
             },
+            # Return input transcript so guardrails can inspect user speech.
+            "inputAudioTranscription": {},
             # Return output transcript so clients can read what the model said.
             "outputAudioTranscription": {},
         }