Descript has a couple of indistinguishable-from-magic features powered by AI: First, you can rearrange audio just by editing the text transcription of that audio, and second, you can also edit what was actually said. There’s a web page1 to demo this amazing feature. It’s based on technology Descript acquired called Lyrebird. Being able to change what someone said has ethical implications with respect to deepfakes, and Descript addresses this on their ethics page. In particular, it only allows you to edit your own voice:
We believe you should own and control the use of your digital voice. Descript uses a process for training speech models that depends on real-time verbal feedback, ensuring that individuals can only create a text-to-speech model of their own voice. Once created, the user is the owner of their voice and has the sole authority to decide when and how it is used.
Descript also provides cloud-based editing features, like Google Docs. Nick Statt writing for The Verge summarizes Descript’s cloud editing features:
With Descript Podcast Studio, the company’s software now supports simultaneous and collaborative multitrack editing in the style of Google Docs, with changes synced in real time to the cloud.