Typographic social cut — captions, tracked overlays & on-video type, agent-native

*"Add captions in condensed type; hit every word on the hero line; drop the attached clip in as an overlay that appears when I raise my hands; add molecular graphics in the a16z style; grade it."*

chatterbox-ttstalking-headflux-devtranscribewhisper-wordhyperframes-renderffmpeg-overlayffmpeg-colorgradelist_capabilitiesdescribe_capability

Output

Word-hit captions
Timed + tracked overlay
On-video type + graphics
Cinematic grade

Time

one call per layer → a finished vertical cut in minutes

Budget

~$0.30–0.80 per 5–15s cut (talking-head/i2v dominates; captions + overlay + grade are ~$0.001/s each)

Reliability

4.3

Customize this playbook

Fill in the fields below. Your answers are inserted into the complete recipe when you copy it.

public URL of your footage (talking-head / product / b-roll). OR leave blank + fill source_still + vo_line to have the agent build a talking-head.

OPTIONAL — a presenter/product image URL, if you want the agent to generate the base clip.

The spoken hero line, e.g. "We are bringing Livepeer Agent to market." (drives the word-level captions.)

OPTIONAL — a design.md / brand URL. The agent honors it (type, palette, "stillness", "no decoration"…).

e.g. ["#F5E400", "#FF2D9B"] editorial, OR a neutral brand set. Empty = footage is the only colour.

e.g. "condensed all-caps, tight tracking" (editorial) | "sentence-case Inter, balanced wrap" (UI/system)

e.g. "active word yellow slab, spoken white" | "active semibold, spoken muted — weight not colour"

e.g. "a16z molecular network" | "capability ticker" | "none — default to stillness"

cinematic | warm | cool | vibrant | bw | none

0-1 fraction of frame (0=left, 1=right)

0-1 fraction of frame (0=top, 1=bottom)

0.05-1.0 relative width (e.g. 0.30)

when it appears

when it leaves