diff --git a/litellm/llms/openai/transcriptions/whisper_transformation.py b/litellm/llms/openai/transcriptions/whisper_transformation.py
index dc46918874b..2c01156fe05 100644
--- a/litellm/llms/openai/transcriptions/whisper_transformation.py
+++ b/litellm/llms/openai/transcriptions/whisper_transformation.py
@@ -133,7 +133,7 @@ class OpenAIWhisperAudioTranscriptionConfig(BaseAudioTranscriptionConfig):
         try:
             raw_response_json = raw_response.json()
         except json.JSONDecodeError:
-            content_type = raw_response.headers.get("content-type", "")
+            content_type = raw_response.headers.get("content-type", "").lower()
             if "application/json" in content_type:
                 raise
             return TranscriptionResponse(text=raw_response.text)