The updated Amazon Polly Generative engine delivers more natural and accurate speech with low latency through a new underlying model. This advancement includes 14 new voices across nine locales, with new languages Hindi and Finnish among them, enabling richer and more precise text-to-speech experiences.
The upgrade facilitates better pronunciation of complex inputs such as numbers and addresses, reducing the need for manual fine-tuning. The service supports existing voice control via Speech Synthesis Markup Language (SSML) and is suitable for applications in contact centers, e-learning, media, and accessibility. Additionally, the Generative offering expanded to AWS GovCloud, serving regulated sectors.
Source & further reading
Polly Generative engine upgraded with more natural speech, 14 new voices, and 2 new languages ↗Source published 2026-10-20. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.