BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//HTUA9X
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-MXECWT@pretalx.devconf.info
DTSTART;TZID=EST:20260924T162000
DTEND;TZID=EST:20260924T163500
DESCRIPTION:Community organizations often possess hundreds of hours of inva
 luable oral histories and archival footage but lack the resources to trans
 form them into accessible\, shareable stories at scale. Griot and Grits: S
 torykeeping Collective is addressing this challenge by partnering with Red
  Hat OpenShift AI to build a fully automated\, open-source AI pipeline for
  documentary production.\n\nIt explores the design and implementation of a
 n event-driven workflow that converts raw interview footage into completed
  mini-documentaries. Attendees will learn how Kubeflow Pipelines orchestra
 te an 11-stage workflow from video ingestion and transcription to entity e
 xtraction\, script generation\, AI narration\, generative B-roll creation\
 , automated video assembly\, and archival storage. It also discusses repla
 cing proprietary AI services with open-source alternatives\, including Aut
 omatic Speech Recognition (ASR)\, Large Language Models served with vLLM\,
  Text-to-Speech (TTS)\, and generative video models\, all deployed on Red 
 Hat OpenShift AI.\n\nBeyond the technical architecture\, this talk highlig
 hts how modern MLOps practices\, containerized AI models\, event-driven au
 tomation\, and resilient pipeline design can empower nonprofit organizatio
 ns to preserve cultural heritage at unprecedented scale. By dramatically r
 educing manual production effort\, the platform enables storytellers to fo
 cus on the narratives that matter while ensuring community histories remai
 n accessible for future generations.
DTSTAMP:20260823T232150Z
LOCATION:106 (Capacity 45)
SUMMARY:Scaling Community Storytelling with Open-Source AI: Building an End
 -to-End Video Processing Pipeline on Red Hat OpenShift AI - Khushi Teli
URL:https://pretalx.devconf.info/devconf-us-2026/talk/MXECWT/
END:VEVENT
END:VCALENDAR