Two-Person Dialogue 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.

Two people talk it through, one of them already a fan: two lip-synced presenters, 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: two presenter portraits (nano_banana_2), a lyria_3_5 music bed, and two eleven_v3 presenter voices each lip-synced with veed_fabric_1_0, then a render and a topaz_video finish. Shots: the first person asks, the second answers with the product, and both hold the product on the end card. Default hooks: Question, Us vs Them flash, Curiosity.

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, render, topaz_video

Example output

https://skills.varg.ai/previews/varg-studio-dialogue.mp4 — From varg's 'No Excuses – Long-Form Dialogue' template (88 s, kling-v3 with native dialogue and captions; pinned to the Two-Person Dialogue shelf of varg's gallery): a walk-and-talk where one woman raises the doubt and the other, already a fan, answers. Cut 28.5-36.5 s. (credit: varg, https://varg.ai)

Used for

More talking heads & avatars skills