FINDING #4944 · UNIT ID 1152193330
OpenMOSS/MOSS-TTS
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
2% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
8.71
ACCEL
+0.86
RETENTION
58.8%
PEAK 2026-07-13 · FORK-RETENTION 0.0% · 61 STARS / WINDOW
Author Audience
AUDIENCE
7,357
FOLLOWERS
765
OWNER ★
29,134
Engagement Signals
FORKS
336
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 61 / 61 (DIVERSITY 1.00)
Why This Is A Finding
OpenMOSS/MOSS-TTS собрал 61 звёзд за окно, тогда как у автора всего 765 подписчиков — эффективная аудитория ≈ 7,357. Это даёт surprise-индекс 0.00118 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 28% OF 6892 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6892 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 28%
VELOCITY8.714.14+4.57ABOVE 71%
RETENTION58.8%40.6%+18.2 PPABOVE 75%
FORKS33689+247ABOVE 80%
SURPRISE0.000.01-0.01ABOVE 15%