From 2f0d8080d1d25287e7ef0286dba71afa8eec9404 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Fri, 22 May 2026 18:23:05 +0000 Subject: [PATCH] fix(gemini realtime): default responseModalities to AUDIO in delta events Align return_new_content_delta_events with the AUDIO defaults used in _handle_session_update and transform_session_created_event so deferred session config does not produce TEXT-typed delta events for audio data. Co-authored-by: Yassin Kortam --- litellm/llms/gemini/realtime/transformation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/litellm/llms/gemini/realtime/transformation.py b/litellm/llms/gemini/realtime/transformation.py index d17fb428668..aa99cc3695f 100644 --- a/litellm/llms/gemini/realtime/transformation.py +++ b/litellm/llms/gemini/realtime/transformation.py @@ -541,7 +541,7 @@ class GeminiRealtimeConfig(BaseRealtimeConfig): generation_config = session_configuration_request_dict.get( "generationConfig", {} ) - 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) ]