Write or paste a script, pick a voice, and get audio back - in a voice you cloned from a 30-second sample, or one of the presets that ship with the app.
You are billed by the second of audio actually delivered, and you start with 500 seconds. A generation that fails costs nothing, asking for exactly the same thing twice costs nothing the second time, and cancelling halfway bills only the part that was already made.
A script is rarely one block of text. Stories is a multi-clip timeline: generate line by line, trim and reorder, layer music underneath, keep the take you prefer when you regenerate one, and export the whole thing as a single file.
