Using the Conversational Style - Amazon Polly

Using the Conversational Style

The Conversational style is available only when using the neural engine, for the Matthew and Joanna voices in US English (en-US). To use the Conversational style, first choose the neural engine and then use the syntax described in the following steps in your input text.


To use any neural speaking style, you must use one of the AWS Regions that support neural voices. This option is not available in all Regions. For more information, see Feature and Region Compatibility.

To apply the Conversational style (console)

  1. Open the Amazon Polly console at

  2. Ensure that you are using an AWS Region where neural voices are supported.

  3. On the Text-to-Speech page, for Engine, choose Neural.

  4. Choose the SSML tab.

  5. Add input text to your text-to-speech request using the Conversational style SSML syntax.

To apply the Conversational style (CLI)

  1. In your API request, include the engine parameter with the neural value:

    --engine neural
  2. Add input text to your API request using the Conversational style SSML syntax.

Use the following Conversational style SSML in your input file.

<amazon:domain name="conversational">text</amazon:domain>

For example, you might use the conversational tag with the Matthew or Joanna voice in the following quotation from H.G. Wells's novel War of the Worlds:

<speak> <amazon:domain name="conversational"> No one would have believed in the last years of the nineteenth century that this world was being watched keenly and closely by intelligences greater than man's and yet as mortal as his own; that as men busied themselves about their various concerns they were scrutinised and studied perhaps almost as narrowly as a man with a microscope might scritinise the transient creatures that swarm and multiply in a drop of water. </amazon:domain> </speak>

For more information about SSML, see Supported SSML Tags.