Transcript-Cut Multicam Podcast — trending format 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.

Sync three cameras, cut the episode from its transcript, and add question cards and pull-quotes in code.

What it does

A long podcast edited from its transcript: three camera angles synced, cuts chosen from the text, and graphics added in code (a "Tech sales, explained" lower third, question cards such as "Which one pays better?", pull-quote cards over the speakers). Omah edited a 40-minute episode this way with Claude and Remotion and was surprised how few tokens it used. An agent transcribes with Whisper, aligns the angles by audio, switches cameras by speaker and cuts by story, renders cards and captions in HyperFrames or Remotion, and exports the long form plus vertical clips.

Status

A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.

Example: https://x.com/TassyOmah_/status/2105312463172358590

How an agent would make it: Multicam footage → Whisper transcript → audio sync → speaker-based angle switching + text-driven cuts → lower thirds, question and quote cards in code → long-form + 9:16 clips

Models it drives: whisper, render

Example output

https://skills.varg.ai/previews/want-transcript-cut-podcast.mp4 — Phone video of her monitor playing the podcast Claude edited from the transcript: cuts between a two-shot and close angles, a 'Which one pays better?' question card and a pull-quote banner (11.5–19.5 s of 29 s) (credit: Omah (@TassyOmah_), https://x.com/TassyOmah_/status/2105312463172358590)

More talking heads & avatars skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.