DemonGatanjieuandClaude Opus 5.5 721a006b16 refactor(audio): drop F5-TTS, the audio page manages GPT-SoVITS only ...

The F5-TTS voice library (input/F5-TTS scanning, voice upload with ffmpeg
conversion, romanization, Load Audio clip drags) and the engine switch are
removed. The audio page now works with one engine, Anomalous_TTS
(GPT-SoVITS): characters, drags onto its node, the Script Director with
direct generation, pronunciation and settings. The audio gallery and its
stream route stay (output and temp folders only). The root PATH hack that
existed for F5-TTS's ffmpeg lookup is gone. Recorded as AD-016.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-09-29 13:53:07 +08:00

..

assets

style(ui): make anime archive background vivid and clear with runic blueprints and transparent grid

2026-09-10 23:27:46 +08:00

modules

refactor(audio): drop F5-TTS, the audio page manages GPT-SoVITS only

2026-09-29 13:53:07 +08:00

styles

refactor(audio): drop F5-TTS, the audio page manages GPT-SoVITS only

2026-09-29 13:53:07 +08:00

hash_resolver.js

feat(toolbox): add unified model source hub with workflow sync and note node generation

2026-09-15 16:17:52 +08:00

main.js

fix(perf): stop a :has() rule from slowing canvas dragging (v1.57.2)

2026-09-26 19:20:03 +00:00

styles.css

refactor(audio): drop F5-TTS, the audio page manages GPT-SoVITS only

2026-09-29 13:53:07 +08:00