Descript – A collaborative audio/video editor that works like a doc

Re:Descript – A collaborative audio/video editor that works ... by krackers on Tuesday January 05, 2021 @04:08AM (#25643633)

Their TTS alone is very convincing. Seems to be better than what Google and Amazon have to offer https://www.descript.com/overdub

[ Parent | on HN ]

Re:Descript – A collaborative audio/video editor that works ... by ffpip on Tuesday January 05, 2021 @05:33AM (#25644103)

They use Google for TTS.

https://www.descript.com/security

[ Parent | on HN ]

Re:Descript – A collaborative audio/video editor that works ... by mandiantBob on Tuesday January 05, 2021 @10:43AM (#25646659)

This is not correct. The security page only shows that they use Google for Speech to Text.

Instead, Text to Speech is done using technology developed by Lyrebird.ai, which Descript has bought over. Descript rebranded it as Overdub. Note that style transfer learning of voices is a hard problem and Overdub seems to have nailed it perfectly. I speculate that the underlying technology of Overdub is based on sv2tts (https://arxiv.org/abs/1806.04558).

The closest comparision to Overdub would be https://www.resemble.ai/.

[ Parent | on HN ]

Re:Descript – A collaborative audio/video editor that works ... by harryparkdotio on Tuesday January 05, 2021 @08:37AM (#25645328)

This was hands down one of the best security pages I've ever read. Incredibly clear, concise and to the point

[ Parent | on HN ]