Amazon Polly logo

Amazon Polly

Transforms text into natural-sounding speech using deep learning technology.

Made by Amazon Web Services

  • Developer Tools

  • Api

  • tts-sdk

What is Amazon Polly?

Amazon Polly is an advanced Amazon AI service that uses deep learning technologies to transform text into lifelike speech. With 47 human-like voices across 24 languages, Polly enables the creation of speech-enabled applications that can work in diverse markets and regions. Developers can leverage Polly's text-to-speech capabilities to build entirely new categories of products that talk, from audiobooks and podcasts to virtual assistants and smart devices. By providing natural-sounding male and female voices, Polly's machine learning-powered speech synthesis allows users to send text through the service's API and receive high-quality audio output in standard formats like MP3 and OGG. The service also supports lexicons and SSML tags, giving developers granular control over various aspects of the generated speech

Highlights

  • Wide language support with 47 lifelike voices across 24 languages
  • Capability to create speech-enabled applications for diverse markets
  • Text-to-speech transformation using advanced deep learning technologies
  • Support for standard audio formats like MP3 and OGG
  • Lexicon and SSML tag support for customizing speech output

Platforms

  • Desktop Linux
  • On-Premise Linux
  • Mobile iPhone
  • Desktop Windows
  • Desktop Mac
  • Mobile Android
  • Web-based
  • Desktop Chromebook
  • Online
  • Mobile iPad
  • Cloud, SaaS, Web-based
  • On-Premise Windows

Languages

  • English

Features

    • Text to Speech