Talking Head Ad — workflow skill for talking heads & avatars

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

A presenter speaks to camera about the product: lip-synced portrait, two b-roll shots, captions, end card.

What it does

Being extracted from varg Studio, where this format is hard-coded today (formats.ts); there is no SKILL.md yet. Recipe: a presenter portrait (nano_banana_2), a lyria_3_5 music bed, an eleven_v3 presenter voice lip-synced with veed_fabric_1_0, and two 5 s b-roll shots of the product and the product in use (minimax_h3_max_turbo for drafts, kling_v3_standard for finals), then a render and a topaz_video finish. The voiceover uses lines like "So, [pain]. I tried [product]". Default hooks: Question, Confession, Bold claim.

Use when

Install

Not published as a standalone skill yet. Source: vargHQ (internal: studio-app/plugins/varg-studio/src/shared/formats.ts)

Models it drives: nano_banana_2, lyria_3_5, eleven_v3, veed_fabric_1_0, minimax_h3_max_turbo, kling_v3_standard, render, topaz_video

Example output

https://skills.varg.ai/previews/varg-studio-talking-head.mp4 — varg's 'Talking Head Promo' template (its TSX, talking-head-varg-promo.tsx, is also shown on varg.ai/platform): a Soul presenter portrait voiced with ElevenLabs v3 and lip-synced with VEED Fabric 1.0 (the same voice and lip-sync models as Studio's Talking Head recipe), a music bed, word-by-word captions and a logo overlay — 'Varg AI is just insane…'. First 8 s of 11 s. (credit: varg, https://varg.ai/ugc-ads)

More talking heads & avatars skills