diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 6fcf789dc1b..6977e18f0fd 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -13966,6 +13966,10 @@ async def audio_transcriptions(
 
         fastapi_response.headers.update(response_headers)
 
+        if data.get("response_format") in ("text", "srt", "vtt"):
+            from fastapi.responses import Response as FastAPIResponse
+            return FastAPIResponse(content=response.text, media_type="text/plain")
+
         return response
     except Exception as e:
         await proxy_logging_obj.post_call_failure_hook(