EJClaw f585ed7b76 feat(voice): bracketed emotion tags, [잡음] for noise, spoken emotion, concise replies ...

- Brain persona now prefixes every reply with one bracketed emotion tag
  (e.g. [반가움], [궁금]) and keeps replies to one or two short sentences.
- Empty/unrecognised audio (silence/noise) is reported as reply "[잡음]" with
  no TTS playback instead of an empty reply.
- TTS speaks the bracketed emotion too: "[힘차게] 안녕!" is synthesised as
  "힘차게, 안녕!" via a leading-tag -> spoken-word transform.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-08-22 01:44:25 +09:00

..

__init__.py

feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

2026-08-09 02:16:14 +09:00

capture_mss.py

feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

2026-08-09 02:16:14 +09:00

claude.py

feat(voice): bracketed emotion tags, [잡음] for noise, spoken emotion, concise replies

2026-08-22 01:44:25 +09:00

melo_worker.py

perf(voice): warm up STT+TTS workers before signalling ready

2026-08-18 21:06:23 +09:00

melo.py

fix(voice): stop backtick TTS crash and actually count error turns

2026-08-18 23:29:13 +09:00

mock.py

feat: live status dashboard for the voice loop

2026-08-16 20:24:13 +09:00

whisper_worker.py

perf(voice): warm up STT+TTS workers before signalling ready

2026-08-18 21:06:23 +09:00

whisper.py

feat(dashboard): browser STT recognition test on the GPU

2026-08-18 21:49:03 +09:00