How-to guides

• Create dialogue with multiple speakers

  Create engaging dialogue with voices that support multiple speakers.

• Use device profiles for generated audio

  Apply device-specific profiles to synthetic speech.

• Create voice audio files

  Synthesize audio file from text or SSML input.

• List all supported voices

  List all of the supported voices for text-to-speech synthesis.

• Specify a regional endpoint

  Configure a regional endpoint for text-to-speech synthesis.

• Decode base64-encoded audio

  Convert base64 encoded data into audio files.