Agent Video Style Kit — effect skill for captions & subtitles
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. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
Cut30's title and caption style kit for 9:16 and 16:9: JSON your agent reads plus an HTML preview. Runnable in varg's code2video templates.
- Type: Effect · Captions & subtitles
- Slug:
cut30-agent-video-style-kit - Status: live
- Publisher: Cut30 (vendor)
- License: Cut30 terms: use and customize for personal or commercial videos, keep Cut30 attribution on the kit page
- Source: https://cut30.co/guides/agent-video-style-kit
- Works in: Claude Code, Codex, Cursor
- Requires: bun, ffmpeg, Google Chrome or Chromium, python3 (only for kit.py validate/embed)
- Cost: Free: renders locally, no varg API key. Transcribing the audio for word timings through the varg API is billed separately.
- Runtime: about 3 s for the 6 s example per ratio; one ffmpeg pass over your footage
What it does
Cut30's Agent Video Style Kit (https://cut30.co/guides/agent-video-style-kit) stores your title and caption style in one JSON file your editing agent reads, with separate specs for 9:16 (1080x1920) and 16:9 (1920x1080): TikTok Sans, a white rounded title bar, white captions with a dark outline at 2-3 words per chunk, exact positions, an alternative caption spot above the head, line limits and suggested safe zones. It comes with an HTML preview page, a schema, a validator (kit.py) and agent instructions: say "use my video style guide" and the agent applies it. Free from Cut30, no account. varg's code2video templates repo ships the kit unmodified with a renderer (render.ts) that burns its title and timed captions onto footage from words.json or an SRT and flags text that wraps too far or enters a safe zone; local, no credits.
Use when
- "Use my video style guide": the same titles and captions on every short
- Burn a transcript or SRT onto a talking-head video as 2-3 word captions
- Set up a title and caption style kit for an editing agent, for 9:16 and 16:9
- Check that captions stay inside platform safe zones and line limits
Not for
- Transcribing audio (get words.json from varg transcription or Whisper first)
- Animated karaoke or anime-style captions (use anime-jp-subtitles or caption-styles)
- Generating footage (use varg-ai)
Install
- Claude Code:
git clone --depth 1 https://github.com/vargHQ/code2video-templates ~/code2video-templates && ln -s ~/code2video-templates/agent-video-style-kit ~/.claude/skills/agent-video-style-kit - setup-prompt:
Paste Cut30's setup prompt from https://cut30.co/guides/agent-video-style-kit into your agent (downloads https://cut30.co/agent-video-style-kit/agent-video-style-kit.zip and verifies its SHA-256). - Any agent, with the vargai CLI:
vargai install cut30-agent-video-style-kit
Example output
https://s3.varg.ai/files/194b94d0-58ff-4e8b-91de-4f1959d04013/file_8eb82edbc04b.mp4 — Rendered with the template itself: bun render.ts --title "Your title, your captions" --text "…" --duration 7, the 9:16 and 16:9 examples side by side on the kit's schematic scene. (credit: Cut30 kit, rendered by varg, https://cut30.co/guides/agent-video-style-kit)
More captions & subtitles skills
- 3D Camera Captions: Captions that live in 3D around a talking head: the camera flies through the words, heroes pass behind the speaker.
- Remotion Captions: Transcribe speech and burn in animated captions with Remotion, or import an existing SRT file.
- ElevenLabs Speech to Text: Transcribe audio and video with word timestamps, speaker labels and keyterms, ready for subtitles.
- ElevenLabs Speech to Text (inference.sh): Transcribe audio with ElevenLabs Scribe, speaker diarization and forced alignment, via inference.sh.
- Speech to Text: Transcribe audio with ElevenLabs Scribe v2 or Whisper V3 Large, with timestamps and speaker labels.
- Pretext Text Metrics: Measure and fit text without the DOM using pretext: auto-fit sizes, know line breaks before render, canvas/WebGL text.
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.
- Any agent with a terminal:
curl -fsSL https://varg.ai/install | sh(Windows:irm https://varg.ai/install.ps1 | iex), thenvargai loginand every model is a command —vargai generate_video …,vargai estimate_cost …(https://varg.ai/how-to/cli/) - 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 <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - 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