Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-10-04 01:25:18 -07:00
Code Issues Packages Projects Releases Wiki Activity
743 Commits 72 Branches 27 Tags
d4a16292c852313c4aa2ff494c4b8151a245cb35
Commit Graph
4 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
devangkanthariaandcapy-ai-staging[bot] 615aeaeb35 fix(kokoro): trim trailing silence and run-on noise on short prompt synthesis (#960) 2026-10-04 00:01:24 +00:00
devangkanthariaandcapy-ai-staging[bot] 38389db82b fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923) 2026-10-04 00:01:18 +00:00
devangkanthariaandcapy-ai-staging[bot] ca56137ca0 fix(settings): invalidate capture-readiness on auto_refine toggle (#753) 2026-10-04 00:00:08 +00:00
devangkanthariaandcapy-ai-staging[bot] 0e1e9922a8 fix(dictation): skip LLM readiness gate when auto_refine is off (#753) 
When the user disables auto_refine (LLM polish) in Settings, the Qwen
refinement model is no longer required for dictation to arm. Previously,
canRecord checked llmReady unconditionally, so useChordSync called
disable_hotkey whenever Qwen was not downloaded -- even if the user
never intended to use refinement.

Changes:
- useDictationReadiness: gate llmReady behind autoRefine in canRecord,
  missing, and the polling predicates so hotkeys arm with just Whisper
  STT when refinement is off.
- DictationReadinessChecklist: hide the LLM row when autoRefine is
  false -- the checklist now shows only Whisper STT.

Closes #753
 2026-10-04 00:00:08 +00:00