Getting Started with Amazon Polly

Amazon Polly is a service that turns text into lifelike speech. Using Amazon Polly, developers can create applications that talk or help developers build entirely new categories of speech-enabled products. Polly allows for configuring Lifelike male or female voices - including bilingual voices that can switch between languages.
Some key features of Amazon Polly include:

- Lifelike Voices - Amazon Polly offers dozens of lifelike voices across a variety of languages and variants. This includes Male and Female voices in US English and other languages. Developers can choose the voice that best fits their needs.

- Text to Speech - Developers can input raw text or SSML into the Polly API and generate high-quality audio files. This allows building apps or services that speak to users. Text can also be synthesized and streamed directly to speakers without the need for storing audio files. 

- Customization - Text can be customized using SSML for controlling output like voice, speech rate, pitch and more. Voices can also be tailored using voice IDs for variants within a language. This allows matching voices to different types of content.

- Usage Flexibility - Audio streams are generated on-demand and don't need to be stored. Audio files like MP3 are also returned for offline usage. This flexibility suits many contexts from streaming playback to downloaded content.

- Low Latency- Polly provides near real-time processing with latency averaging under 100ms. This enables building conversational interfaces and real-time speech applications.

- SDKs & Integration - SDKs are available for popular languages/platforms like Java, Python, .NET, JavaScript and Mobile platforms. APIs also integrate with services like Lex, Rekognition and Amazon CloudFront for building complete solutions.

That covers some of the key features of Amazon Polly.

Comments

Popular posts from this blog

Getting Started with Amazon Athena

Getting Started with AWS Config

AWS Identity and Access Management (IAM)