AWS – Four new synthetic generative voices for Amazon Polly
Today, we are excited to announce the general availability of four highly expressive Amazon Polly voices speaking in American and Australian English.
Amazon Polly is a managed service that turns text into lifelike speech, allowing you to create applications that talk and to build speech-enabled products depending on your business needs.
The generative engine is Amazon Polly’s most advanced text-to-speech (TTS) model. With this launch, we add a variety of new synthetic generative English voices to Polly portfolio: i.e., an Australian English voice Olivia, and three US English voices Joanna, Danielle, and Stephen. These voices sound similar to our neural voices with the same names, but they have much more natural pronunciation and prosody. Our customers can use this high-tier product in various industries and for different purposes: e.g., education, publishing, marketing, etc.
Danielle, Joanna, Olivia, and Stephen generative voices are accessible in the US East (North Virginia), Europe (Frankfurt), and US West (Oregon) regions and complement the other types of voices that are already available in the same regions.
For more details, please read the Amazon Polly documentation and visit our pricing page.
Read More for the details.