Synthesise a spoken line as a WAV.

Synthesises a line of English as a 44.1 kHz WAV with the engine's own voice. The voices are synthesised by the engine, never cloned from a recording, and no voice can be uploaded. seed varies the voice; woman, age (0 to 1) and machine shape it; speed (0.5 to 2) sets how fast it speaks (1 is the speaker's own); rate sets the sample rate. Every line comes back at one loudness (level_db, default -16 dBFS of speech, so lines from different voices sit together on a timeline and none clips; level_db false leaves the voice's own level) and with its silence trimmed to a breath either side (trim false keeps the voice's half-second tail). text is at most 1000 characters, and a line that presents itself as spoken by a real, famous person is refused. Costs 1 unit.