~/talk

Soyoung Lee, TwelveLabs | AWS Summit NYC 2025

links:none on file
slides:none on file

Company claims a multimodal video understanding stack that ingests video, audio and text to create searchable embeddings and run video-language tasks at scale. It ships an embedding model Marengo and a video-language model Pegasus, exposes APIs and a turnkey search engine, and supports major vector stores including S3 Vector Store. Deployments index videos into embeddings, add a search API (demoed in ~20 minutes), and serve media, sports, ad tech and safety customers across petabyte libraries with 50,000 developer users and ~110 staff.

AI-written summary · about

~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.