Amazon Polly launches gated voice cloning from a few minutes of audio

AWS ML Blog · rss · 2026-11-20

AWS announced general availability (gated release) of Amazon Polly voice cloning. With 1-10 recordings from a consenting speaker, CreateVoice builds a custom voice in 5-10 minutes, synthesized by Polly's generative engine with similar naturalness to existing generative voices.

Key points

Available in all regions supported by the Polly generative engine; access is open to select customers, others can apply.

Original post →

More from Multimodal

Multimodal channel →