domains / families / media / create-creator-takes-h3

create-creator-takes-h3

separate

Generate an AI creator talking to camera, saying an approved script, as one continuous track — H3 Max reference-to-video through the GooseWorks fal-proxy (charged to your GooseWorks credits). Plans takes on line boundaries under H3's 15s cap, dry-runs a cost estimate, generates the first take alone so its voice can be locked and passed to every later take, joins takes with measured 0.10s dissolves, and moves each line's timing onto the words actually spoken. Use for any format with a generated creator speaking a script (split-screen, screen inserts, talking-head ads).

When to use

• Generate AI creator talking to camera
• H3 Max reference-to-video generation
• Plan takes on line boundaries under 15s cap
• Dry-run cost estimate
• Generate first take to lock voice
• Join takes with 0.10s dissolves
• Move line timing onto spoken words
• Split-screen, screen inserts, talking-head ads

When not to use

• Hand-filling character-prompt.json
• Video above 768P unless customer asks
• Studio or shallow focus unless reference is shot that way
• Forced flaws or marks unless user chose them
• Skin condition unless product treats it
• Action shots (person who acts)

Skill page

Source