From 14613f8b2fc2a85dc0db905799a659e4ff68913d Mon Sep 17 00:00:00 2001
From: dfatima504 <duaaf200215@gmail.com>
Date: Sat, 27 Jun 2026 16:42:53 +0500
Subject: [PATCH] fix(proxy): return text/plain for audio transcriptions when
 response_format=text/srt/vtt

---
 litellm/proxy/proxy_server.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index b49d8ad7965..510a1391d5e 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -9643,6 +9643,10 @@ async def embeddings(
             version=version,
         )
 
+        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:
         # Use unified error handler