AWS says the release improves speech naturalness, expressiveness, and accuracy while retaining low latency.
The update adds 14 voices across nine locales. The Generative engine now has 57 voices across 11 languages and 25 locales. Generative voices for Hindi and Finnish are generally available for the first time. AWS also says the engine can better reflect emotion and prosody from textual context without manual configuration.
For existing users, AWS describes this as a drop-in upgrade: voice names and API calls are unchanged, so applications using existing generative voices should continue to work without code changes. The source provides illustrative audio examples, including numbers, currency, and addresses, but does not establish independent quality measurements, comparative benchmarks, or any pricing change.