Bearer token

Output languages. Lite supports 1, Standard up to 2, and Pro up to 4. The first is primary; each additional delivered language is billed +6 credits.

Optional visual-style preset — expressed through typography, palette, motion, image treatment and pacing. Orthogonal to `scenario` (it does NOT change routing). `auto` (default) lets the director pick; every other value adopts a real named look: `cinematic` = dark film-noir (black + blood-red, Oswald); `glass` = Apple / iOS-26 frosted liquid glass; `luxury` = timeless near-black + indigo, huge whitespace; `swiss` = precise grid + electric blue + oversized numerals; `modern` = clean light SaaS; `editorial` = cream magazine + serif; `warm` = intimate cream + amber; `vibrant` = festive folk colour; `neon` = electric neon glow; `mono` = grayscale, type-led; `pastel` = soft candy pastels; `bold` = huge poster type; `industrial` = raw glitch + rust; `futuristic` = particle glow. A freeform string is also accepted as a soft hint.

Optional narration voice — the **timbre** of the voiceover, independent of language. `auto` (default) lets the director pick a fitting voice. Every preset is cross-lingual: the same voice speaks whatever language(s) you set in `langs`, so choose purely by character — `warm-female`, `bright-female`, `anchor-female`, `clean-female`, `calm-male`, `deep-male`, `documentary-male`, `energetic-male`, `storyteller-male`. Advanced: a raw 32-character Fish `reference_id` is also accepted. For `drama` / `avatar` this sets the primary / narrator timbre; distinct characters may still get their own.

Production action. Lite supports generate/edit; Standard adds remix; Pro adds extend. remix/edit/extend require `ref_task_id`.

Required output aspect ratio. Lite renders 720p/24fps; Standard and Pro render 1080p/30fps.

Natural-language brief describing the video to produce (the topic, what to show, tone, audience). The agent decides the script, visuals, voiceover and edit.

Production SKU. `lite` = fast 720p short video at 0.20 credits/s (up to 30s); `standard` = balanced 1080p at 0.60 credits/s (up to 120s); `pro` = advanced production at 1.20 credits/s (up to 300s). Default: standard.

Target video length in seconds. Lite: 5–30; Standard: 5–120; Pro: 5–300. Successful jobs are billed by actual delivered duration, never above the requested duration.

Production route. Lite supports auto/narrated/captions; Standard adds avatar; Pro adds drama. `captions` requires source video in `file_urls`; `avatar` requires a portrait. avatar bills at 1.15× and drama at 1.35×.

Optional reference media (image / video / audio URLs) the agent can use — e.g. a product shot or logo to feature, footage to caption.

Required when `action` is remix / edit / extend: the task_id of the previous video to start from.

Optional. Fired with the result when the task reaches a terminal state (succeeded / failed).