video1.0<iframe src="https://www.loom.com/embed/9739fc87167c498fae3eb8575e927acd" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/9739fc87167c498fae3eb8575e927acd-92f2e28f5f16c3eb.gif199.387This Loom explains Recall.ai’s native transcription service and how to choose between low latency and high accuracy modes. Low latency streams near-instant text chunks suitable for use cases like closed captioning. High accuracy can take 3 to 10 seconds to 3 to 10 minutes and supports inputs for language identification, profanity filtering, improved spelling, and keyword identification for industry jargon. The presenter demonstrates both modes in a Google Meet using two Recall AI meeting bots, showing low latency streaming partial output while high accuracy returns a larger, more accurate transcript after about 45 seconds.