tts-voice-creator-clone-and.../static
mARTin-B78 d16be50cc9 Fix STT health check incorrectly marking Open WebUI as whisper.cpp
Port 8080 is Open WebUI — it passes /health + /v1/models checks but
returns 405 on POST /v1/audio/transcriptions. Updated probe logic to:
- treat 405 as 'endpoint missing, try next path'
- treat non-JSON 500 as broken, JSON-500 with detail as 'audio too short' (ok)
- use 500ms silence WAV instead of 1-frame (too tiny for alignment models)

Changed whisper.cpp default from :8080 to :8085 to avoid clash with
Open WebUI. Updated s-llms.html placeholder and code snippet accordingly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-28 09:03:21 +02:00
..
sections Fix STT health check incorrectly marking Open WebUI as whisper.cpp 2026-05-28 09:03:21 +02:00
app.js Surface real STT error detail instead of raw HTTP noise 2026-05-28 08:23:05 +02:00
index.html Add Conversation Playground + XTTS v2 backend + VibeVoice voice fix 2026-05-27 23:27:57 +02:00
loader.js Add Conversation Playground + XTTS v2 backend + VibeVoice voice fix 2026-05-27 23:27:57 +02:00
nav.js Add Conversation Playground + XTTS v2 backend + VibeVoice voice fix 2026-05-27 23:27:57 +02:00
style.css Add Conversation Playground + XTTS v2 backend + VibeVoice voice fix 2026-05-27 23:27:57 +02:00