--- title: "Turn a Product Page Into a Narrated YouTube Walkthrough — AI video generator workflow for launch videos" description: "Product or feature page to a 45-60 s narrated walkthrough: Playwright screenshots, Remotion, OpenAI TTS voiceover, YouTube upload and page embed. Install in Claude Code, Codex and Grok with one command." url: https://varg.ai/how-to/skills/product-walkthrough-video-to-youtube updated: 2026-10-31 --- # Turn a Product Page Into a Narrated YouTube Walkthrough — workflow skill for launch videos > **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q="` 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 `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install ` with no key, every varg model after `vargai login`. Product or feature page to a 45-60 s narrated walkthrough: Playwright screenshots, Remotion, OpenAI TTS voiceover, YouTube upload and page embed. - **Type:** [Workflow](https://varg.ai/how-to/workflows.md) · [Launch videos](https://varg.ai/how-to/browse/skills/launch.md) - **Slug:** `product-walkthrough-video-to-youtube` - **Status:** live - **Publisher:** vood (community) - **Source:** https://github.com/vood/claude-launch-video-skill/tree/main/launch-video - **Works in:** Claude Code ## What it does A 7-step pipeline: read the feature, capture real screenshots of production with Playwright at 1920x1080 (banners hidden), build a 30 fps Remotion video with scenes sized to their narration, generate per-scene voice-over with gpt-4o-mini-tts and an emotion instructions prompt, mux and encode a sub-10 MB upload cut, upload unlisted to YouTube for approval, then add a click-to-play embed and announce it. Needs ffmpeg, Node, youtubeuploader, an OpenAI key and a Google OAuth client with YouTube Data API v3. ## Use when - Make a launch, feature or walkthrough video - Add a voice-over to a product video - Upload and publish a video to YouTube - Add videos to your top-traffic pages at scale ## Install - Claude Code: `cp -r launch-video /path/to/your/project/.claude/skills/` - Any agent, with the vargai CLI: `vargai install product-walkthrough-video-to-youtube` ## More launch videos skills - [Orbit Card](https://varg.ai/how-to/skills/hyperframes-orbit-card.md): A single feature card orbits a dot sphere on a Blender-made camera move: a 10-second product beat. - [Higgsfield Academy (Higgsfield Open-Source Promo)](https://varg.ai/how-to/skills/higgsfield-open-higgsfield-academy.md): Higgsfield's 64 s promo for Higgsfield Academy, made almost entirely with Seedance 2.0. - [Seed Audio 1.0 Launch (Higgsfield Open-Source Video)](https://varg.ai/how-to/skills/higgsfield-open-seed-audio-launch.md): Higgsfield's 106 s launch video for Seed Audio 1.0 (voice cloning, cinematic sound): bold motion design, comedic tone. - [HeyGen's Real Launch Videos as HyperFrames Source](https://varg.ai/how-to/skills/heygen-hyperframes-launch-videos-source.md): 20 HeyGen product launch videos as editable HyperFrames HTML compositions, each with its storyboard, assets and render command. - [Onetake](https://varg.ai/how-to/skills/onetake.md): Launch films that never cut to the next slide: one continuous camera, measured moves, motion blur, a slideshow oracle. - [Guizang Product Video](https://varg.ai/how-to/skills/guizang-product-video.md): Software promos and release-notes videos built from your real product components, with original music and SFX. ## 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`), then `vargai login` and 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 -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