AWS now offers long-form engine with the first three expressive American English voices
Today, we are excited to announce the general availability of the highly expressive long-form engine with the first three American English Amazon Polly voices available to our customers in the US.
Today, we are excited to announce the general availability of the highly expressive long-form engine with the first three American English Amazon Polly voices available to our customers in the US.
Amazon Polly is a 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 new long-form engine is the premium product tier of Polly Text-to-Speech (TTS), represented by three American English voices: i.e., Danielle, Gregory, and Ruth. To offer this novel type of synthesized natural-sounding speech, we have reinvented neural Polly voices with cutting-edge deep learning TTS technology. The result is human-like, highly expressive, and emotionally adept voices that will be helpful to our customers from media, marketing, and education industries, among many others. We designed the long-form voices with the intent of captivating listeners’ attention to longer content, such as news articles, training materials, or marketing videos. The updated technology opens new opportunities for using this line of the speech product in various use-cases, and we are delighted to release it for our customers.
Danielle, Gregory, and Ruth long-form voices are accessible in the US East (North Virginia) region and complement the other 13 en-US voices that are already available for developing speech products for a variety of use cases. For more details, please read the Amazon Polly documentation and visit our pricing page.