From the source
Amazon has made voice cloning in Amazon Polly generally available as a gated release, letting customers build a custom voice from a few minutes of a consenting speaker's recordings.
- The cloned voices run on the Amazon Polly generative engine, which Amazon says delivers similar naturalness and accuracy as the rest of its generative voices.
- Voice cloning launches with seven languages — English, Spanish, German, French, Italian, Portuguese and Hindi — and each cloned voice speaks only the language it was recorded in.
- Cloned voices are automatically encrypted and access-controlled, so only the customer can access them.
- The feature is available in all AWS Regions supported by the generative engine, including AWS GovCloud (US), with access already enabled for select customers; others can contact their AWS account team or apply for access.
- Building a cloned voice is free, and Amazon charges for cloned voice usage on a pay-as-you-go basis.
- Customers create a voice by calling CreateVoice with 1-10 recordings and TermsAccepted=True, wait 5-10 minutes while it builds and is checked for speaker similarity, then pass the voice ID to SynthesizeSpeech or StartSpeechSynthesisTask.






