Polly Generative engine upgraded with more natural speech, 14 new voices, and 2 new languages

Amazon Polly Generative Engine Update

Amazon Polly now features a new model delivering more natural-sounding and accurate speech output with low latency. This upgrade includes an enhanced voice portfolio with higher quality, 14 new voices across nine locales, and two new languages—Hindi and Finnish. 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).

The Generative engine now supports complex content such as numbers, email addresses, and street addresses with improved reliability. You can continue using Speech Synthesis Markup Language (SSML) tags for speech output control. The low-latency streaming API is ideal for contact center experiences, chatbots, and large language model (LLM) based voice applications.

The new Generative voices are 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).

What to do

• Explore the new voices on the Amazon Polly Features page.
• Read the Amazon Polly documentation for more details.
• Check the pricing page for costs.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.