<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/1ccd4eec00eb4ddab700d32734f33c28&quot; frameborder=&quot;0&quot; width=&quot;1110&quot; height=&quot;832&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>832</height><width>1110</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>832</thumbnail_height><thumbnail_width>1110</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1ccd4eec00eb4ddab700d32734f33c28-7c2ab43df91dc831.gif</thumbnail_url><duration>154.8311</duration><title>Openscribe</title><description>In this video, I introduce OpenScribe, a free MIT licensed AI medical scribe that transcribes audio and generates structured clinical notes. It can run in the browser or as a desktop Electron app, allowing for seamless audio capture during clinician-patient conversations. The architecture is similar to commercial AI scribe software, making it a reusable core infrastructure for anyone interested. I encourage you to clone the repo and run it locally, keeping in mind that it&apos;s currently not HIPAA compliant without your own hosting setup. Check the readme for a quick five-minute setup and clear documentation.</description></oembed>