<?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/d60eec26390048f2a4e9e623633fb825&quot; frameborder=&quot;0&quot; width=&quot;1612&quot; height=&quot;1209&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1209</height><width>1612</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1209</thumbnail_height><thumbnail_width>1612</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/d60eec26390048f2a4e9e623633fb825-e235878f09e0d63e.gif</thumbnail_url><duration>103.603</duration><title>Introducing Speaker Label Correction for Improved AI Transcriptions</title><description>Hey everyone, in this video, I’m excited to share a new feature that allows you to correct speaker labels in our AI-generated transcripts. We know that AI can sometimes get confused, especially in noisy environments, and historically, you haven’t had a way to address this yourself. Now, if you notice incorrect speaker labels, you can flag the call, specify who should be labeled as first and second speaker, and confirm the changes. This will ensure that all summaries and coaching are accurately applied to the right person. I encourage you to try this out and help us improve the accuracy of our transcripts!</description></oembed>