<?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/0ec572aa1e6f4231b382bb3f865b56d2&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/0ec572aa1e6f4231b382bb3f865b56d2-aeb117fd4bf0a627.gif</thumbnail_url><duration>368.714</duration><title>RakerOne Structured Audio Extraction Demo</title><description>This Loom demonstrates RakerOne’s structured audio extraction and workflow automation using medical scribe style outputs. The presenter defines an action called MedicalScribeExtraction with structured fields such as chief complaint, assessment bullet points, plan, and follow up, then runs it across 10 to 30 minute MP3 call recordings uploaded in a project container. Processing takes about 30 seconds per file, using transcription with diarization plus a parallel quality model, shown alongside the transcript for validation (green checkmarks with example confidence of 4 out of 5). The results are editable with logged approvals and access controls, and the same approach can be run in batch or via API, with additional support for SIP streaming and PDF extraction.</description></oembed>