Today, we are introducing a new model behind the Amazon Polly Generative engine that delivers more natural-sounding, accurate speech output with low latency. With this upgrade, you get access to an enhanced voice portfolio with higher overall quality, 14 new voices across nine locales, and two new languages—Hindi and Finnish—now generally available on the Generative engine for the first time. New voices include Kenneth and Nate (US English), Russell and Curtis (Australian English), Kiara and Arjun (Hindi and Indian English), Tina (German), Carlos (US Spanish), Leo and Carolina (Brazilian Portuguese), Hyunduk (Korean), and Suvi (Finnish).
Amazon Polly is a fully managed service that turns text into natural-sounding speech. This drop-in model upgrade makes Generative voices more natural and accurate. Complex content such as numbers, email addresses, and street addresses is designed to sound more reliable, reducing the need to fine-tune speech output. You can continue to use Speech Synthesis Markup Language (SSML) tags to control speech output on the Generative engine, just as before. The low-latency streaming API makes it easy to build contact center experiences, chatbots, and large language model (LLM) based agentic voice applications for real-time conversations. The richness and variety of voice options are also well suited for news, media, entertainment, e-learning, and accessibility use cases. This launch also expands the Amazon Polly Generative offering to AWS GovCloud, providing more options for public sector and regulated industries.
All new Generative voices are now available in the following AWS Regions: US East (N. Virginia), US West (Oregon), Europe (Frankfurt), Europe (Zurich), Europe (London), Asia Pacific (Sydney), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Tokyo), Canada (Central), and AWS GovCloud (US-West).
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.
Categories:
Source: Amazon Web Services
