Podcast clip & audiogram — how to make it with code and an AI agent
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
A podcast moment for the feed: the waveform, the captions, who is speaking, where to listen.
Output: 1:1 or 9:16 · 30–90 s · Input: An audio clip and its transcript
To make it with AI models (footage, voice, music) instead: the step-by-step use case.
Skills that make it end to end
Recipe, beat by beat
Each beat lists components that build it; install any with its command, then fill its slots.
Show (Logo stings, Lower thirds)
- Liquid Thorn Logo — Any word as a black-metal chrome logo that a cursor smears with a WebGL fluid. ·
git clone https://github.com/vargHQ/code2video-templates && cd code2video-templates/liquid-thorn-logo && bun render.ts --text "WORD" - Beat Accent — A single music-hit sting: impact flash, micro scale-pulse on the subject, immediate decay. ·
npx hyperframes add beat-accent - Extruded Logo — Beveled 3D letters flip up one by one, the word swings so light runs across the bevels, then settles for a readable hold. Chrome, gold or ma ·
npx hyperframes add extruded-logo - Lower Third — BILD Style — News-style lower third with tight-fit text boxes: white headline bar with red drop-shadow, red sub-line with white drop-shadow. ·
npx hyperframes add lower-third-bild - Lower Third — Accent Underline — Cardless lower third for footage overlay: name rises, an accent rule draws left-to-right, role fades in; text-shadowed for legibility ·
npx hyperframes add lt-accent-underline - Lower Third — Bold Block — High-energy podcast lower third: solid dark block wipes in, uppercase name slams up, accent tag pops ·
npx hyperframes add lt-bold-block
Clip (Audio visualizers, Captions & subtitles)
- Oscilloscope Trace — CRT oscilloscope beam sweeping a waveform across a 10x8 graticule, with closed-form phosphor persistence: the tail decays as exp(-age/tau) a ·
npx hyperframes add oscilloscope-trace - Waveform — Equalizer bars in a blue to pink gradient pulse across the middle of the frame, like an audio visualizer. A WebGPU shader from the Shaders l ·
npx hyperframes add waveform - Anime JP Subtitles — Japanese captions in four anime styles from one subs.json: fansub lines with a karaoke sweep, TV telop with popping letters, a vertical tate ·
git clone https://github.com/vargHQ/code2video-templates && cd code2video-templates/anime-jp-subtitles && bash make.command - varg Music Video — An AI music video from a song: song map with beats and word timings, a beat-grid storyboard, Seedance scenes with QA, a frame-exact cut on t ·
git clone https://github.com/vargHQ/code2video-templates && python3 code2video-templates/varg-music-video/scripts/songmap.py song.mp3 --lyrics lyrics.txt --out songmap.json - Blend Difference — Auto-inverting text using mix-blend-mode: difference — flips between white and black per-pixel against the background ·
npx hyperframes add caption-blend-difference
Speakers (Lower thirds, Layouts & grids)
- Lower Third — BILD Style — News-style lower third with tight-fit text boxes: white headline bar with red drop-shadow, red sub-line with white drop-shadow. ·
npx hyperframes add lower-third-bild - Lower Third — Accent Underline — Cardless lower third for footage overlay: name rises, an accent rule draws left-to-right, role fades in; text-shadowed for legibility ·
npx hyperframes add lt-accent-underline - Lower Third — Bold Block — High-energy podcast lower third: solid dark block wipes in, uppercase name slams up, accent tag pops ·
npx hyperframes add lt-bold-block - Anime Triple Split — Three live video panels slam onto screentone paper one per beat — ink borders, slanted gutters, an impact flash and a katakana SFX stamp — t ·
git clone https://github.com/vargHQ/code2video-templates && cd code2video-templates/anime-triple-split && bash make.command - Browser Device Stage — A generic app surface in token-native device chrome (browser, window, or phone). The screen is a slot for caller img/video/HTML with a token ·
npx hyperframes add browser-device-stage - Card Resize — A transitions.dev-inspired card resize primitive that expands a compact card into a detail panel ·
npx hyperframes add card-resize
Listen (CTAs & end cards)
- CTA Close — A display-scale action line lands per word and fills the frame with air, one generous CTA capsule pops beneath it with a single overshoot, a ·
npx hyperframes add cta-close - CTA Lockup — A canonical closing lockup that reveals an action line, pops in an accent CTA capsule, settles supporting microcopy, and holds with confiden ·
npx hyperframes add cta-lockup - Logo Brand Close — A display-scale wordmark cascades letter by letter into a centered lockup, the accent brand period lands last, an optional tagline and wide- ·
npx hyperframes add logo-brand-close
Across the whole video: Captions & subtitles
Generated footage, voice and music
Code renders the layout for free. Anything generated — AI shots, voiceover, music, lip-sync — runs on varg with one key: npx skills add vargHQ/skills --skill varg-ai, the Claude Code plugin claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg, or the MCP https://mcp.varg.ai/mcp.