Api.audio allows you to organise content in a way that is optimised to programatically create professional sounding audio. The central component to do this is the script. While you can create Speech directly from text via a direct call to the text-to-speech API or you can only use the rendering engine in isolation, it usually makes sense to create a script and generate speech or fully produced audio based on that. Further, you can upload or record audio and make it available to be used in what you want to create.
Updated about 1 month ago