From 7e275c1daa47d3963cefc469cc26c2aeae21c56d Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Fri, 8 May 2026 19:05:28 +0200
Subject: [PATCH] fix: prevent STT from blocking the uvicorn event loop
 (#24338)

The transcription endpoint was async but called the synchronous transcribe() function directly, blocking the single-threaded uvicorn event loop for the entire duration of inference. This caused all HTTP and WebSocket connections to stall for every user on the instance during STT processing.

- Add asyncio import

- Use async UploadFile.read() instead of synchronous file.file.read()

- Offload the blocking transcribe() call via asyncio.to_thread()

Closes #24169
---
 backend/open_webui/routers/audio.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/backend/open_webui/routers/audio.py b/backend/open_webui/routers/audio.py
index c653a370e0..f0a1e54fc9 100644
--- a/backend/open_webui/routers/audio.py
+++ b/backend/open_webui/routers/audio.py
@@ -1,3 +1,4 @@
+import asyncio
 import hashlib
 import json
 import logging
@@ -1258,7 +1259,7 @@ async def transcription(
         id = uuid.uuid4()
 
         filename = f'{id}.{ext}'
-        contents = file.file.read()
+        contents = await file.read()
 
         file_dir = os.path.join(CACHE_DIR, 'audio', 'transcriptions')
         os.makedirs(file_dir, exist_ok=True)
@@ -1277,7 +1278,7 @@ async def transcription(
             if language:
                 metadata = {'language': language}
 
-            result = transcribe(request, file_path, metadata, user)
+            result = await asyncio.to_thread(transcribe, request, file_path, metadata, user)
 
             return {
                 **result,