Apple Music Lyric Video — trending format for music videos
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.mdto its path. Before generating anything, show the person the options on the use-case page.
A phone lyric screen: the sung line big and bold, the rest dimmed and blurred, synced word by word to a song.
- Slug:
want-apple-music-lyric-video - Status: wanted
- Publisher: Jeff Guo (community)
- Source: https://x.com/immasiddx/status/2074152481555386804
- Cost: ~25 credits / run (estimate) — Lyria 3.5 ~11 per song + Whisper ~6 + render ~6 (varg catalog of 2026-10-23); a song the user uploads skips Lyria.
What it does
A screen recording of a streaming app's full-screen lyrics view: the active line is large and white, neighboring lines fade and blur with distance, and the list spring-scrolls on every line. It took off with Jeff Guo's "Claude's Plan", a dev-culture parody whose lyric-screen clip reached 1.7M views in one X repost and, by the creator's count, 190K Douyin likes in a day. An agent generates an original song from the user's lyrics with Lyria 3.5 or ElevenLabs Music v2.5, force-aligns word times with Whisper to the known lyrics (Jeff used stable-whisper and librosa for the drops), and renders an in-house lyric player in HyperFrames with an optional album-art header, mesh-gradient background and translation line. varg puts the song, the timing and the render on one credit balance.
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/immasiddx/status/2074152481555386804
How an agent would make it: Song (Lyria 3.5 / ElevenLabs Music v2.5, or upload) → Whisper word timestamps force-aligned to the known lyrics → lyric JSON → HyperFrames lyric player (active line bold, blur by distance, spring scroll) → 9:16 export
Models it drives: lyria_3_5, eleven_music_v2_5, whisper, render
Example output
https://skills.varg.ai/previews/want-apple-music-lyric-video.mp4 — Screen recording of the full-screen lyrics view for Jeff Guo's song 'Claude's Plan': the active line is big and white, neighbors blur, the list scrolls line by line (6–14 s of 48 s, muted) (credit: Jeff Guo (@jeffgwoah), via sid (@immasiddx), https://x.com/immasiddx/status/2074152481555386804)
Used for
- AI music video: A music video for your song: concept, a consistent lead character, shots cut on the beat, lip-sync on vocals.
- Lyric video: Lyrics synced to the song: the sung line big and highlighted, karaoke-style, over art or a shader.
More music videos skills
- Music Video Director: Direct an AI music video the way top X creators do: song map, beat-grid storyboard, stills first, Seedance, lip-sync.
- Prod by Claude: A square video of a Strudel live-coding track where every code token lights up on the note it plays.
- Motion Graphics Music Video: Animated character music videos from your song and a prompt: storyboard, fal generation, p5 motion graphics, VFX.
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 <agent> -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