Amazon Polly expands Generative TTS engine with 10 new voices, 2 new regions, and Bidirectional Streaming API
Today, we are excited to announce the general availability of 10 new highly expressive Amazon Polly Generative voices across 8 locales: Tiffany (American English), Brian (British English), Aria (New Zealand English), Jasmine (Singapore English), Florian (French), Ambre (French), Lorenzo (Italian), Beatrice (Italian), Lennart (German), and Sabrina (Swiss German).
Alongside these new voices, we have expanded the Generative engine to two new AWS regions in Europe (London) and Canada (Central). We have also introduced the Bidirectional Streaming API support for the Generative engine, allowing customers to stream text to Polly and receive synthesized audio back simultaneously. This makes it easy to feed output directly from a large language model (LLM) into speech synthesis, enabling real-time applications like chatbots and bespoke characters in games.
Amazon Polly is a fully managed service that turns text into lifelike speech. This expansion addresses the growing demand for natural-sounding, lifelike speech generation in conversational AI and content creation. Developers building LLM-based interactive systems and speech-enabled applications can take advantage of the enhanced voice quality and variety, expanded language and feature support, as well as broader AWS region availability.
To hear how Polly voices sound, go to Amazon Polly Features. For more details on the Polly offerings and use, see the Amazon Polly documentation and pricing page.
All new Generative voices are now available in the US East (North Virginia), Europe (Frankfurt), US West (Oregon), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Tokyo), Europe (London), and Canada (Central).