Amazon Polly

Amazon Polly is a service that converts text into lifelike speech, enabling you to create applications that speak and develop entirely new categories of speech-enabled products. Polly's Text-to-Speech (TTS) service uses advanced deep learning technologies to generate natural-sounding human speech.

Actions

  • listLexicons - Return a list of pronunciation lexicons stored in an AWS region

  • synthesisspeech - Synthesis UTF-8 input, plain text, or SSML to a stream of bytes

  • getLexicon - Return the content of the specified pronunciation lexicon stored in an AWS region

  • describevoices - Return a list of voices available for use in speech synthesis requests

  • putLexicon - Store a pronunciation lexicon in an AWS region

  • getspeechsynthesistask - Retrieve a specific speechsynthesis taskobject based on its TaskID

  • listspeechsynthesistaskd - Return a list of spechsynthesis Task objects ordered by their creation date

  • startspeechsynthesistask - Allows the creation of an asynchronous synthesistask, by starting a new speechsynthesis Task

  • deleteLexicon - Delete the specified pronunciation lexicon stored in an AWS Region