Skip to main content
Audio assets are reusable recordings or uploaded media for supported voice experiences. Pronunciation dictionaries manage Arabic and French pronunciation audio entries.

​
Reusable audio

Use Audio to upload, record, organize, and play assets. An asset can supply a consistent greeting or prompt for a supported playback step. Spoken text and prerecorded audio are different ways to communicate the same message during a Voice flow. An uploaded asset can require processing before playback is available. In API responses, check file.playable rather than assuming a successful upload means the file is ready.

​
Pronunciation dictionaries

Use Dictionaries to manage pronunciation audio entries. Review and listen to entries before relying on them in a supported voice configuration. A dictionary is a pronunciation resource, not a knowledge base of answers. Next: Flows and Audio and Dictionaries API.