Community organizations often possess hundreds of hours of invaluable oral histories and archival footage but lack the resources to transform them into accessible, shareable stories at scale. Griot and Grits: Storykeeping Collective is addressing this challenge by partnering with Red Hat OpenShift AI to build a fully automated, open-source AI pipeline for documentary production.

It explores the design and implementation of an event-driven workflow that converts raw interview footage into completed mini-documentaries. Attendees will learn how Kubeflow Pipelines orchestrate an 11-stage workflow from video ingestion and transcription to entity extraction, script generation, AI narration, generative B-roll creation, automated video assembly, and archival storage. It also discusses replacing proprietary AI services with open-source alternatives, including Automatic Speech Recognition (ASR), Large Language Models served with vLLM, Text-to-Speech (TTS), and generative video models, all deployed on Red Hat OpenShift AI.

Beyond the technical architecture, this talk highlights how modern MLOps practices, containerized AI models, event-driven automation, and resilient pipeline design can empower nonprofit organizations to preserve cultural heritage at unprecedented scale. By dramatically reducing manual production effort, the platform enables storytellers to focus on the narratives that matter while ensuring community histories remain accessible for future generations.