You use Text-To-Speech API to send synthesized speech or recorded sound files to a phone number. You can:
- Create synthesized audio messages that are delivered in a language, accent and gender personalized for your users.
- Personalize message presentation by changing the speaking rate and introducing pauses.
This section briefly explains the:
Text-To-Speech API workflow
To use the Nexmo Text-To-Speech API you:
- Create a Text-To-Speech using the request.
Note: set callback in the request so you receive the Text-To-Speech Return Parameters at your webhook endpoint.
- Receive a Response and check the Response codes to ensure that you sent the request to the Nexmo correctly.
- Using your script at the webhook endpoint, check the Text-To-Speech Return Parameters to see:
- If the status was successful.
- When and how the Text-To-Speech was made.
- How much the Text-To-Speech cost.
Note: remember to return 200 ok when you receive the Text-To-Speech Return Parameters.