Amazon Polly's new generative engine is a technology that enables the creation of human-like synthetically generated voices. It was introduced as part of the Amazon Polly service, which is a machine learning (ML) service that converts text to lifelike speech using text-to-speech (TTS) technology. The generative engine was trained with publicly available and proprietary data, across a variety of voices, languages, and styles, and is capable of rendering context-dependent prosody, pausing, spelling, dialectal properties, foreign word pronunciation, and more. It supports four voice engines: standard, neural, long-form, and generative voices. The generative engine can be used to create voices for knowledgeable customer assistants, virtual trainers, or experienced marketers.

To use Amazon Polly's generative voices, you can access them through the AWS Management Console, AWS Command Line Interface (AWS CLI), or the AWS SDKs. Here's a brief guide on how to get started:

• Go to the Amazon Polly console in the US (N. Virginia) Region.
• Choose the Text-to-Speech menu in the left pane.
• Select the voice of Ruth or Matthew for English (US), or Amy for English (UK), and choose the Generative engine.
• Input your text and listen to or download the generated voice output.

For CLI usage, you can list the voices with the generative engine using the command:

$ aws polly describe-voices --output json --region us-east-1 |
  jq -r '.Voices[] | select(.SupportedEngines | index("generative")) | .Name'

And synthesize speech to an audio file with the command:

$ aws polly synthesize-speech --output-format mp3 --region us-east-1 \
  --text "Hello. This is my first generative voices!" \
  --voice-id Matthew --engine generative hello.mp3

For more code examples using AWS SDKs, you can visit the Code and Application Examples in the AWS documentation.

The new generative voices of Amazon Polly are available in the US East (N. Virginia) Region. Users can select from the new voices and utilize them for various applications and use cases. The voices are accessible through the Amazon Polly console, AWS CLI, or AWS SDKs, and users are charged based on the number of characters of text converted to speech.