open-webui/backend
Classic298 6faf540310
fix: show the speech engine's reason when it refuses a transcription (#32186)
When an OpenAI-compatible speech-to-text engine or Deepgram rejected a recording, the error shown after dictating only gave the HTTP status, such as "429 Too Many Requests", and the engine's own reason, such as "Quota exceeded" or "Invalid credentials.", was lost. The error now shows that reason. When the engine sends no reason, the HTTP status is shown as before.

Fixes #32009
2026-10-10 20:00:51 +04:00
..
data refac: mv backend files to /open_webui dir 2024-09-04 16:54:48 +02:00
open_webui fix: show the speech engine's reason when it refuses a transcription (#32186) 2026-10-10 20:00:51 +04:00
.dockerignore fix: litellm config issue 2024-02-24 22:35:11 -08:00
.gitignore refac 2024-09-06 04:59:20 +02:00
dev.sh perf: allow disabling websocket per-message-deflate (#28613) 2026-08-24 18:46:07 -04:00
requirements-slim.txt refac 2026-10-05 12:03:19 +04:00
requirements.txt chore: bump rapidocr to 3.10.0 to drop the duplicate OpenCV install (#32125) 2026-10-09 12:49:12 +04:00
start.sh refac 2026-09-06 16:48:30 -04:00
start_windows.bat chore: drop nltk, unused at the pinned versions (#29725) 2026-09-06 16:39:05 -04:00