Descript delivers a modern video editing experience, built on AI that enables users to modify spoken language in audio and video on the fly by simply modifying a transcript. The platform also allows you to synthetically generate a speaker’s voice to add content to any video as well. Each step is complex, as they have to apply AI and reliably process the video, orchestrating asynchronous, end-to-end processes using Temporal Workflows.
Key takeaways
In this 45-minute session, Descript Staff Software Engineer Nathan Wesling goes over:
