muapi-music-video

Generate N keyframes in parallel via muapi image generate using scene-specific prompts with the visual_style, using model nano-banana-pro.
Create one music track via muapi audio create (kind=music) using the music_style with a duration of N x 5 + a 2s tail.
Animate each keyframe in parallel via muapi video from-image with model veo3.1-image-to-video, duration=5, and scene-specific motion direction prompts.
Return scene keyframes, animation clips, music track asset ids in order, and a short summary describing the cut order.

theme (text, required) — Song / video theme.
scenes (int, optional, default 3) — Number of scenes; each becomes a 5s clip.
music_style (text, optional, default: ambient cinematic, instrumental, slow tempo, warm) — Suno-style tags for the soundtrack.
visual_style (text, optional, default: cinematic, photoreal, soft volumetric light, 16:9).

Do not auto-confirm any single video call > 50 cr; user confirmation is required (the loop will prompt automatically).
Each scene is a fixed 5s clip.
Music duration equals N x 5 + a 2s tail.
Character continuity depends on repeating the character description verbatim in every scene prompt.
Confirm MUAPI_API_KEY is set or run muapi auth configure before calling muapi CLI commands.
Substitute {{input_name}} placeholders (theme, scenes, music_style, visual_style) with actual user inputs before issuing each call.
Prompt the user before confirming any single video call costing more than 50 cr.
If a scene's muapi video from-image fails after failover, fall back to muapi video generate (text-to-video) for that scene only.

AI 搜索