Add Audio to a Custom Skill


You can enhance your custom skill with audio. Add short, prerecorded audio, such as sound effects, or stream long-form audio, such as narrative stories.

Options to add audio

The Alexa Skills Kit (ASK) provides several options to integrate audio in a custom skill:

  • To add short, prerecorded audio, such as sound effects, within a voice response, add the Speech Synthesis Markup Language (SSML) audio tag to your skill. With the audio tag, you provide the URL for an MP3 file that the Alexa service plays with a voice response.
  • To add short, prerecorded audio along with a visual response on Alexa-enabled devices with a screen, use Alexa Presentation Language (APL) for Audio. You can mix audio with Alexa speech and sync your visuals with layered sound effects and background music.
  • To stream long-form audio, such as podcasts, news stories, and live streams, add the audio player interface to your skill. Alexa reports the audio playback state to your skill, such as when the track is nearly finished, or when the playback stops. For more details, see Stream Long-Form Audio with AudioPlayer.

Alternatively, if you have a music catalog and want to build a skill that lets users play content from the catalog, you can build a music, radio, or podcast skill. These skill types use the pre-built voice interaction model. For more details, see Steps to Build a Music, Radio, or Podcast Skill. Or, if you want to deliver quick snippets of information to users with no user interaction, you can build a Flash Briefing skill.


Was this page helpful?

Last updated: Jan 26, 2024