Amazon Polly launches voice cloning: A unique voice for your brand
Machine Learning Blog
Amazon Polly voice cloning is now generally available as a gated release, allowing users to create custom synthetic voices from speaker recordings.
- Create cloned voices from 1-10 recordings (up to 15 minutes total) with speaker consent
- Supports seven languages: English, Spanish, German, French, Italian, Portuguese, and Hindi
- Voice creation typically takes 5-10 minutes and is free; usage charged on pay-as-you-go basis
- Cloned voices are encrypted, access-controlled, and scoped to the AWS account that created them
- Use cases include brand consistency, contact centers, media production, localization, and accessibility
- Available in 11 AWS Regions including GovCloud; initial quota of 10 voices per account per region
- Generated speech includes watermarks; recordings deleted after voice creation
Voice cloning enables businesses to establish consistent, recognizable brand voices across channels while maintaining speaker consent and data privacy controls.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.