TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

VoiceCraft: Open-source neural codec text-to-speech model with voice cloning

5 点作者 pak大约 1 年前

1 comment

spxneo大约 1 年前
Once in a while you come across a paper or example that just leaves you astounded, this is that. I cannot tell the edited voice, it is seamless and whats shocking is that it doesn&#x27;t care if there is music playing in the background.<p>There&#x27;s just so many ways to abuse this but also lot of hilarious&#x2F;good uses too. Scary times ahead.