OpenAI says it can clone a voice from just 15 seconds of audio

Re:OpenAI says it can clone a voice from just 15 seconds of ... by Plankaluel on Saturday March 30, 2024 @08:31AM (#39874211)

VoiceCraft, which has been released open source a week or so ago, can do the same with 5-10sec audio and is pretty convincing. It's pretty fun to play around with: https://github.com/jasonppy/VoiceCraft

[ Parent | on HN ]

Re:OpenAI says it can clone a voice from just 15 seconds of ... by bijoo on Saturday March 30, 2024 @09:07AM (#39874507)

Submitted multiple times in past few days. Here's a link to the most upvoted one as of now: https://news.ycombinator.com/item?id=39865340 VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (jasonppy.github.io)

[ Parent | on HN ]

Re:OpenAI says it can clone a voice from just 15 seconds of ... by washadjeffmad on Saturday March 30, 2024 @08:48AM (#39874352)

Thanks. TorToiSe has been feeling a long in the tooth, and this looks a little more digestible.

[ Parent | on HN ]