From 159982a8923e456f488fad1994b80437d4e596e4 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Fri, 22 May 2026 18:09:03 +0000 Subject: [PATCH] fix(gemini realtime): default synthetic session.created modalities to AUDIO The synthetic session.created event emitted in deferred setup mode used TEXT as the default for responseModalities, while _handle_session_update defaults to AUDIO. Align the default so clients reading modalities from the initial session.created see the correct value for live sessions. 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 374e57e2fe9..d17fb428668 100644 --- a/litellm/llms/gemini/realtime/transformation.py +++ b/litellm/llms/gemini/realtime/transformation.py @@ -478,7 +478,7 @@ class GeminiRealtimeConfig(BaseRealtimeConfig): generation_config = ( session_configuration_request_dict.get("generationConfig", {}) or {} ) - 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) ]