EJClaw 4db73bf69f feat(voice): express [감정] tags via pitch/speed instead of speaking them ...

Emotion tags now steer delivery rather than being read aloud. parse_segments()
splits a reply on [감정] tags: a recognised emotion word switches the pitch and
speed of the text that follows (and is dropped), while a non-emotion bracket
(e.g. [1번]) keeps its inner words as spoken content. Emotions can change
mid-reply, so a single turn is synthesised as several pitch-shifted segments and
concatenated in the melo worker (librosa pitch_shift, warmed at startup).

The emotion vocabulary is grounded in Azure Neural TTS speaking styles plus
Ekman's basic emotions, with Korean synonyms. The brain persona is updated to
emit inline tags from that set.

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

2026-08-22 10:14:49 +09:00

5.9 KiB

Raw Blame History

View Raw