Make sound effects and place them on their takes (costs credits)

Each effect is made with ElevenLabs sound generation from its prompt, duration_s long (0.5-6), brought to -20 LUFS so the effects layer's one level fits them all, added to the film's sounds (kind effect) and placed on its take at at_s seconds into the clip (target as in mutations: {kind: "segment", id} | {kind: "loop", decisionId} | {kind: "ending", panelId}), at level (0-2, times the effects layer), pitch (semitones, -12 to 12) and rise (dB it starts under). The same prompt and length twice is made once and placed twice, the second at another pitch. The player plays an effect where that second of the clip is on screen (through trims and ramps), dipped under speech. Placing an existing sound is free: {op: "addEffect", target, takeId, effect: {id, soundId, atS, level?, pitch?, rise?}}, updateEffect {target, takeId, id, patch}, removeEffect {target, takeId, id}. Costs credits: audio_sfx_10s per 10 s rendered (see /v1/pricing). Quote first with dry_run: true: credits, and renders (each sound to make, its credits and how many places it goes). Without dry_run it answers 202 { task_id }: poll GET /v1/tasks/{id}. Each sound is charged once it is on the storyboard, through your token so its daily cap applies. Paid tier only (402 audio_requires_purchase on trial credits). A storyboard whose owner approves agent spending answers 403 except for the quote.