From the source
Amazon upgraded the Generative engine behind Polly, its managed text-to-speech service, saying the new version produces more expressive and accurate speech at low latency.
- The upgrade adds 14 voices across 9 locales, including the first generally available Generative voices in Hindi and Finnish, bringing the catalog to 57 generative voices across 11 languages and 25 locales.
- Amazon says it is a drop-in change: voice names and API calls are unchanged, so existing applications keep working without code changes, and the upgrade happens in place for applications already using Generative voices.
- Region availability expands to AWS GovCloud (US-West), for a total of 11 AWS Regions.
- Amazon says the improved voice quality and accuracy come at the same pay-as-you-go price, with no cost increase, no new SKU and no changes to existing integrations, and cached static prompts can be replayed at no additional cost.
- The engine supports the SynthesizeSpeech API and the Bi-Di Streaming API StartSpeechSynthesisStream for real-time streaming, which Amazon says suits voice agents and game characters.