FINDING #7153 · 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
3.27
ACCEL
-0.01
RETENTION
32.7%
PEAK 2026-08-12 · FORK-RETENTION 81.3% · 98 STARS / WINDOW
Author Audience
AUDIENCE
8,238
FOLLOWERS
909
OWNER ★
32,130
Engagement Signals
FORKS
366
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 98 / 98 (DIVERSITY 1.00)
Why This Is A Finding
OpenMOSS/MOSS-TTS собрал 98 звёзд за окно, тогда как у автора всего 909 подписчиков — эффективная аудитория ≈ 8,238. Это даёт surprise-индекс 0.000395 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 81.3% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 25% OF 9593 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9593 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 25%
VELOCITY3.273.63-0.37ABOVE 45%
RETENTION32.7%25.0%+7.7 PPABOVE 65%
FORKS366117+249ABOVE 77%
SURPRISE0.000.01-0.01ABOVE 10%