There are two answers to this question depending on how you capture your audio/video.
1. If your speakers are on separate tracks, you can use our multitrack feature. This will allow for automatic speaker labeling. It's also a bit more accurate since the speakers are isolated on separate tracks.
You can turn on multitrack upload from the sidebar of the upload page in your account - see the screenshot below:
2. If you don't record speakers on separate tracks we have a feature that can help reduce the amount of manual labeling, but it doesn't remove it entirely. This article explains how it works: https://help.sonix.ai/editing-a-transcript/how-do-i-auto-fill-or-auto-label-speaker-names