API

Questions regarding our APIs

• Where can I get my API key?
• How to get the uuid of the custom voice?
• Can enhanced voices use direct synthesis?
• Can enhanced voices stream?
• Does the API support language selection?
• How to curl your api?
• What is the default audio encoding configuration?
• Is it possible to change the sample rate of the existing clip?
• Do you allow output of the voice audio in mulaw?
• Is the translation from English done automatically?
• Can I implement streaming endpoint?
• Is there a way to bulk upload a bunch of text for audio to be mapped?
• Can the model say the years more colloquially (e.g. Nineteen eighty-four, twenty twenty-three)?
• Is there another tag that will interpret a street address, including common abbreviations street types, states, etc?
• Does this API automatically start training the voice?