跳到正文

Amazon Polly 以受限发布形式正式推出语音克隆功能

AWS Machine Learning Blog当事人· Suyin Wang·· 1 天前精选Amazon Polly launches voice cloning: A unique voice for your brand
打开原文
原文
图片来自 AWS Machine Learning Blog
谁
Amazon Polly
引文
Voice cloning in Amazon Polly is now generally available as a gated release.

发生了什么

Amazon Polly 语音克隆功能现已以受限发布形式正式可用,允许客户利用同意授权的说话人录音创建合成语音,并将其用于生成式引擎。语音创建通常需要 5–10 分钟;克隆语音支持七种语言,但仅能说出所录制的那一种语言。AWS 会在创建完成后删除其录音副本;客户可控制访问权限并可删除该语音。

推荐理由

团队可利用说话人的录音创建品牌化语音,并在 AWS 内管理授权同意、访问权限与删除操作;每个语音仅限于所录制的语言,且必须为账户启用访问权限。

这件事到目前为止

Amazon Polly has made voice cloning generally available as a gated release, allowing customers to create a synthetic voice from recordings of a consenting speaker and use it with its generative engine, according to the AWS Machine Learning Blog. Access is already enabled for select Amazon Polly customers, while others can contact their AWS account team or apply for access. Voice creation typically takes 5–10 minutes, and cloned voices support seven languages while speaking only the language recorded. Building a cloned voice is free for Amazon Polly customers, while cloned voice usage is charged on a pay-as-you-go basis. AWS deletes its copy of the recordings after creation, and customers control access and can delete the voice.

接下来读什么

查看这件事的完整进展Amazon Polly Makes Gated Voice Cloning Generally Available
这条收录于 11月20日 AI 日报看这一期日报的全部内容