Amazon Web Services has reached general availability for voice cloning within its Amazon Polly service. The tool enables users to create a custom voice using only a few minutes of source audio provided by a consenting speaker. Once built, the synthesized profile reads new text inputs in that speaker's distinct voice.
The resulting cloned voices operate directly on the Amazon Polly generative engine. In addition to brand personalization, the feature currently supports seven languages. This setup allows teams to produce synthetic audio across multiple languages provided they have the required permissions from the recorded individual.

