tkrmagid/watch_sceen_ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(tts): raise default glyph speed 1.35 -> 1.4

Browse Source 
Bump the base TTS speed default (WSAI_TTS_SPEED, slider default/label, dashboard
fallbacks) so the bot speaks a bit faster by default.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
EJClaw
2026-08-27 00:00:06 +09:00
parent ed5f328889
commit 7c899d3b19
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
wsai/backends/melo.py
View File

@@ -12,7 +12,7 @@ Env:
WSAI_MELO_DEVICE cpu | cuda | auto (default auto: GPU if torch sees one, WSAI_MELO_DEVICE cpu | cuda | auto (default auto: GPU if torch sees one,
else CPU; the worker falls back to CPU if CUDA fails) else CPU; the worker falls back to CPU if CUDA fails)
WSAI_TTS_OUT_DIR where wavs are written (default ~/.cache/wsai/tts) WSAI_TTS_OUT_DIR where wavs are written (default ~/.cache/wsai/tts)
WSAI_TTS_SPEED glyph speed / length_scale multiplier (0.5..2.0, default 1.35) WSAI_TTS_SPEED glyph speed / length_scale multiplier (0.5..2.0, default 1.4)
WSAI_TTS_WORD_GAP intra-sentence pause delta, sec (-0.2..0.5, default -0.07) WSAI_TTS_WORD_GAP intra-sentence pause delta, sec (-0.2..0.5, default -0.07)
WSAI_TTS_SENTENCE_GAP sentence-boundary silence, sec (-0.5..1.5, default -0.30) WSAI_TTS_SENTENCE_GAP sentence-boundary silence, sec (-0.5..1.5, default -0.30)
WSAI_TTS_PITCH global semitone offset (-12..12, default 0.0) WSAI_TTS_PITCH global semitone offset (-12..12, default 0.0)
@@ -99,7 +99,7 @@ class MeloTTS:
self.out_dir = Path(out_dir or os.environ.get("WSAI_TTS_OUT_DIR") self.out_dir = Path(out_dir or os.environ.get("WSAI_TTS_OUT_DIR")
or (Path.home() / ".cache/wsai/tts")) or (Path.home() / ".cache/wsai/tts"))
self.speed = float(speed if speed is not None self.speed = float(speed if speed is not None
else os.environ.get("WSAI_TTS_SPEED", "1.35")) else os.environ.get("WSAI_TTS_SPEED", "1.4"))
# Reply-global rhythm/pitch controls (see melo_worker.py / docs manual). # Reply-global rhythm/pitch controls (see melo_worker.py / docs manual).
self.word_gap = float(word_gap if word_gap is not None self.word_gap = float(word_gap if word_gap is not None
else os.environ.get("WSAI_TTS_WORD_GAP", "-0.07")) else os.environ.get("WSAI_TTS_WORD_GAP", "-0.07"))

8
wsai/dashboard.py
View File

@@ -520,7 +520,7 @@ class Dashboard:
def _tts_base(self) -> dict: def _tts_base(self) -> dict:
t = self.tts t = self.tts
return { return {
"speed": float(getattr(t, "speed", 1.35)), "speed": float(getattr(t, "speed", 1.4)),
"word_gap": float(getattr(t, "word_gap", -0.07)), "word_gap": float(getattr(t, "word_gap", -0.07)),
"sentence_gap": float(getattr(t, "sentence_gap", -0.30)), "sentence_gap": float(getattr(t, "sentence_gap", -0.30)),
"pitch": float(getattr(t, "pitch", 0.0)), "pitch": float(getattr(t, "pitch", 0.0)),
@@ -1038,8 +1038,8 @@ PAGE = r"""<!DOCTYPE html>
<span id="tEmoNote" class="sttstat">감정을 고르면 그 감정만 따로 조절합니다. 기본(공통)은 태그 없는 말투에 적용됩니다.</span> <span id="tEmoNote" class="sttstat">감정을 고르면 그 감정만 따로 조절합니다. 기본(공통)은 태그 없는 말투에 적용됩니다.</span>
</div> </div>
<div class="ttsgrid"> <div class="ttsgrid">
<label>글자 속도 <b id="tvSpeed">1.35x</b> <label>글자 속도 <b id="tvSpeed">1.40x</b>
<input type="range" id="tSpeed" min="0.5" max="2.0" step="0.05" value="1.35"></label> <input type="range" id="tSpeed" min="0.5" max="2.0" step="0.05" value="1.4"></label>
<label>단어 간격 <b id="tvWord">-70 ms</b> <label>단어 간격 <b id="tvWord">-70 ms</b>
<input type="range" id="tWord" min="-0.2" max="0.5" step="0.01" value="-0.07"></label> <input type="range" id="tWord" min="-0.2" max="0.5" step="0.01" value="-0.07"></label>
<label>문장 간격 <b id="tvSent">-0.30 s</b> <label>문장 간격 <b id="tvSent">-0.30 s</b>
@@ -1460,7 +1460,7 @@ async function pollSTTLoad(target){
// --- 봇 목소리(TTS) 조절: 감정별 슬라이더 → 미리듣기 → 봇 적용 -------------- # // --- 봇 목소리(TTS) 조절: 감정별 슬라이더 → 미리듣기 → 봇 적용 -------------- #
let ttsInited = false; let ttsInited = false;
let ttsState = {base:{}, overrides:{}, emotions:[]}; // last-known server state let ttsState = {base:{}, overrides:{}, emotions:[]}; // last-known server state
const TTS_DEFAULT = {speed:1.35, word_gap:-0.07, sentence_gap:-0.3, pitch:0}; const TTS_DEFAULT = {speed:1.4, word_gap:-0.07, sentence_gap:-0.3, pitch:0};
function ttsLabels(){ function ttsLabels(){
const sp=parseFloat($('tSpeed').value), wg=parseFloat($('tWord').value), const sp=parseFloat($('tSpeed').value), wg=parseFloat($('tWord').value),
sg=parseFloat($('tSent').value), pt=parseInt($('tPitch').value,10); sg=parseFloat($('tSent').value), pt=parseInt($('tPitch').value,10);