Make B-roll Talking Head
Make B-roll Talking Head
Up-to-30s vertical talking-head video: the actor speaks full-frame while a user-supplied b-roll video is overlaid on the lower half (face stays clear up top). REVIEW STYLE — put a line containing only --- in the script to split an INTRO (actor speaks to camera, no b-roll yet — e.g. "Today we are going to review the game of X vs Y") from the MOVES narration after it; the b-roll appears when the moves begin and loop-fills through to the end while the actor narrates, and the moves take continues seamlessly from the intro's last frame and the same voice (guaranteed continuity, not a jump-cut). Without --- it is a plain talking head (<=15s single take; 16-30s two takes) with the b-roll placed via broll_start_time. Provide actor_image_url (any https image) + broll_video_url (any https video — both re-hosted to R2 automatically) and EITHER script (Seedance voice) OR audio_url (your own audio, single clip <=15s). Optional: subtitles; broll_width_rate (0.1-1.0, e.g. 0.8 = b-roll 80% width centered with black margins; omit for full width); broll_start_time (override when the b-roll appears); broll_fade_out (dissolve the b-roll at its end).
When to use this
Call this skill when the user asks for the outcome described above. It runs on the agent-media vNext primitive runtime via the mcp__agent-media__make_broll_talking_head MCP tool. Authentication is the user's existing agent-media Bearer token (issued by agent-media login).
How to call it
Preferred path: MCP tool mcp__agent-media__make_broll_talking_head. Schema is auto-published via tools/list against the same MCP server, so don't restate the schema here — trust the server's response.
Fallback path: REST.
POST https://api.agent-media.ai/v1/skills/make_broll_talking_head/run
Authorization: Bearer $AGENT_MEDIA_API_KEY
Content-Type: application/json
Idempotency-Key: <any unique string per intent>