# 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="` 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. - **Slug:** `want-transcript-cut-podcast` - **Status:** wanted - **Publisher:** Omah (community) - **Source:** https://x.com/TassyOmah_/status/2105312463172358590 - **Cost:** ~12 credits / run (estimate) — Whisper ~6 + render ~6 (catalog of 2026-10-23); the editing itself runs locally. ## 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 - [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. - [Podcast Dialogue Video](https://skills.varg.ai/skills/varg-podcast-video.md): Two-character podcast or debate clips: one studio set, locked camera angles, MiniMax H3 Max with native audio. - [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. ## 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. - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a -y` - Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp` - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt