domains / families / media / render-song-mv

render-song-mv

separate

Assemble a song-driven music-video ad from a config — a generated sung track carries the whole narration across N tableaux (one keyframe -> one i2v clip per lyric beat) with NO separate voiceover, captions synced to the song's OWN word timings (script-window, never Whisper) and the hook word landing on the chorus drop, closed on a PIL brand end card. This is the FREE deterministic assembly stage (clip cut-to-timeline + captions + end card + FFmpeg composite); the song, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the song-driven-music-video format.

When to use

• song-driven-music-video format
• deterministic assembly stage
• clip cut-to-timeline
• lyric-synced captions
• PIL brand end card
• FFmpeg composite
• hard-concatenation on the beat
• muxing master video

When not to use

• generating sung tracks
• generating keyframes
• generating image-to-video clips
• picking creative choices
• using Whisper for captions
• adding separate voiceover
• AI-rendering brand text

Skill page

Source