Urgent.News

What's breaking now, across thousands of outlets.

AI

Amazon Polly launches voice cloning: A unique voice for your brand

Voice cloning in Amazon Polly is now generally available. Give Amazon Polly a few minutes of recordings from a consenting speaker, and it builds a custom voice that reads new text in that speaker's voice. Cloned voices run on the Amazon Polly generative engine and support seven languages.

Amazon Polly, a cloud-based service, has introduced voice cloning as a general release. Users can now create their own cloned voice from a few minutes of audio recordings, provided the speaker has given consent. The cloned voices utilize the same Amazon Polly generative engine, ensuring naturalness and accuracy similar to other voices.

Initially, the feature is available in seven languages: English, Spanish, German, French, Italian, Portuguese, and Hindi. Each cloned voice speaks in the language it was recorded in, and they are automatically encrypted with access control, ensuring only authorized users can access them. Currently, the feature is available in all AWS regions supported by Amazon Polly generative engine, including the AWS GovCloud (US) Region.

Access is already provided for select Amazon Polly customers, while others can apply for it through their AWS account team or by reaching out to Amazon.

With this new feature, users can build the cloning lifecycle into their AWS applications. Building a cloned voice is free for Amazon Polly customers, and usage charges are applied on a pay-as-you-go basis. A user can record a few minutes of audio, and Amazon Polly will create a cloned voice that speaks in the same voice, allowing users to read any text they want.

The cloned voice supports seven languages, and it is demonstrated by a few examples, such as Trevor, a science lead, and his cloned voice, and Jeff Barr, an AWS Chief Evangelist, who uses the cloned voice in various scenarios, such as a non-player character in a game, a support line representative, and a narrator narrating a lesson.

The cloned voices can be used across various applications, including brand consistency, contact centers, media and content at scale, and accessibility and personalization. The voice cloning process involves recording the speaker, creating the voice through the Amazon Polly generative engine, and waiting for the asynchronous creation process, which typically takes 5-10 minutes.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at aws.amazon.com →

More in AI

More from Thursday 19 November →