# Podcast Dialogue Video — 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-character podcast or debate clips: one studio set, locked camera angles, MiniMax H3 Max with native audio.

- **Type:** [Workflow](https://skills.varg.ai/workflows.md) · [Talking heads & avatars](https://skills.varg.ai/browse/skills/talking-head.md)
- **Slug:** `varg-podcast-video`
- **Status:** beta
- **Publisher:** varg (varg, verified)
- **License:** MIT
- **Source:** https://github.com/vargHQ/skills/tree/main/varg-podcast-video
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI, OpenClaw
- **Requires:** varg API key, A reference image per character
- **Cost:** ~450 credits / run (estimate) — The skill's figure for one 9-scene question (5 stills + nine 5 s minimax_h3_max clips); a 12-question episode is ~5,400 credits. Written against the legacy v1 API, so re-check with estimate_cost.

## What it does

A 7-step recipe for two-character dialogue videos: write 5 s scenes with one short line each, generate an empty studio set, compose a wide shot from the character, outfit and set references, derive close-ups and a cold-light "truth cutaway" from that wide shot, then animate each scene with minimax_h3_max image-to-video speaking the line natively. It records what fails (over-the-shoulder shots rearrange the characters; describing appearance swaps the person) and ends with an HTML storyboard that plays every scene in order. The file has no YAML frontmatter yet and calls the legacy `/v1` endpoints, so both need fixing before it is published.

## Use when

- Two-character conversation videos: podcast, interview, debate
- Educational "lie vs truth" formats
- Multi-scene videos where characters must stay consistent across camera angles
- Short-form pieces with 5 s scenes and punchy lines

## Not for

- Over-the-shoulder shots: the model rearranges the characters
- Long monologues: one short line per 5 s scene

## Install

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg`
- Codex: `npx skills add vargHQ/skills --skill varg-podcast-video -a codex -y`
- Cursor: `npx skills add vargHQ/skills --skill varg-podcast-video -a cursor -y`
- Gemini CLI: `npx skills add vargHQ/skills --skill varg-podcast-video -a gemini-cli -y`
- OpenClaw: `npx clawhub@latest install varg-podcast-video`

**Models it drives:** nano_banana_pro, minimax_h3_max

## Example output

https://skills.varg.ai/previews/varg-podcast-video.mp4 — From varg's 'Omega-3: Jesus vs The Devil – AI Podcast' template (15 min, minimax-h3-max with native audio) — the skill's own worked example: one studio set, locked close-ups, Jesus asks and the Devil answers. Cut 9.5-17.5 s. (credit: varg, https://varg.ai)

## Used for

- [Talking avatar or presenter](https://skills.varg.ai/use-cases/talking-avatar.md): A person (from a headshot, or generated) speaks your script to camera with lip-sync, in any language.

## More talking heads & avatars skills

- [Character Keynote](https://skills.varg.ai/skills/varg-character-keynote.md): One render call: a Soul character delivers a keynote-style ad line on a generated stage, voiced by Seedance 2.5.
- [Talking Head Production](https://skills.varg.ai/skills/inference-sh-talking-head-production.md): Produce talking-head videos with AI avatars, lip-sync and voiceover, from portrait specs to final cut.
- [AI Avatar Video](https://skills.varg.ai/skills/inference-sh-ai-avatar-video.md): Create talking-head avatar videos from a portrait and a script, with a lip-synced voice.
- [P-Video Avatar](https://skills.varg.ai/skills/inference-sh-p-video-avatar.md): Turn one portrait into a speaking avatar video with Pruna P-Video-Avatar, its built-in TTS or your audio.
- [AI Podcast Video](https://skills.varg.ai/skills/inference-sh-ai-podcast.md): Generate a multi-person talking-head podcast video from scratch: characters, voices, avatars, stitching.
- [Lanshu AI Presenter Video](https://skills.varg.ai/skills/lanshu-ai-presenter-video.md): Publish-ready explainers led by an AI presenter from an authorized photo, or in one of twelve presenter-free styles.