
- Who
- Amazon Polly
- What
- made generally available gated voice cloning in Amazon Polly
- Quote
Voice cloning in Amazon Polly is now generally available as a gated release.
What happened
Amazon Polly voice cloning is now generally available as a gated release, letting customers create a synthetic voice from recordings of a consenting speaker and use it with the generative engine. Voice creation typically takes 5–10 minutes, and cloned voices support seven languages while speaking only the language recorded. AWS deletes its copy of the recordings after creation; customers control access and can delete the voice.
Why it matters
Teams can create branded speech from a speaker’s recordings and manage consent, access, and deletion within AWS; each voice is limited to the language recorded, and access must be enabled for the account.
The story so far
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.
