A script is our 'unit' of audio. Consider this like your story. Scripts can have many sections within them.
Usage: type Script in your documentation

A script item is an 'item' that you create. This is what you retrieve from the API
Usage: type Script_item in your documentation

Speech is text-to-speech produced by the API. This will have a voice associated with it as well - such as Joanna or Brian
Usage: type Speech in your documentation

Speech Synthesis Markup Language (SSML) is an XML-based markup language for speech synthesis applications. It is a recommendation of the W3C's voice browser working group. As different voice providers and voices support only parts of the SSML standard or extend it with special tags. offers additional guardrails to make your script robust across different voice providers and voices.
Usage: type SSML in your documentation

Each Text to Speech voice or voice cloned voice (specific to each customer) has its' own name.
Usage: type Voice in your documentation

A project consists of modules (which are often optional) but can also consist of scripts. Use this to organise your work.
Usage: type Project in your documentation

Each customer has their own organisation (this is often your company). In some specific cases (like if you're working for an agency) you'll have multiple organisations for the same customer.
Usage: type Organisation in your documentation

Sound design is the art and practice of creating sound tracks for a variety of needs. It involves specifying, acquiring or creating auditory elements using audio production techniques and tools. For us this is a specific kind of 'sound design template' which users of Digital Audio Workstation will be familiar with. If you're not an expert don't worry we have plenty to choose from.
Usage: type Sound_design in your documentation

The application of various audio effects in order to make your audio sound like a professional production.
Usage: type Mastering in your documentation