From f1895265e6b5643ef0e5be97b6f4cd65fcc2e78f Mon Sep 17 00:00:00 2001
From: AlexsanderHamir <alexsanderhamirgomesbaptista@gmail.com>
Date: Mon, 17 Nov 2025 12:55:58 -0800
Subject: [PATCH] fix: increase chunk_size to 8 KB for optimal latency

---
 litellm/proxy/proxy_server.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index cb43ef0cecf..16988205530 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -5236,7 +5236,7 @@ async def moderations(
 async def _audio_speech_chunk_generator(
     _response: HttpxBinaryResponseContent,
 ) -> AsyncGenerator[bytes, None]:
-    _generator = await _response.aiter_bytes(chunk_size=4096)
+    _generator = await _response.aiter_bytes(chunk_size=8192)
     async for chunk in _generator:
         yield chunk