lyric-video-director

Direct synchronized typography-led lyric video production with FFmpeg and master audio preservation.

44|8|Updated Jul 11, 2026
One-click install
npx skills add https://github.com/ShadoW-Shinigami/lyric-video-director --skill lyric-video-director
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lyric-video-director
Source: https://github.com/ShadoW-Shinigami/lyric-video-director/tree/main
Command: npx skills add https://github.com/ShadoW-Shinigami/lyric-video-director --skill lyric-video-director

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, ffprobe, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill turns a song, exact lyrics, and rough timings into a coherent, production-ready lyric video while preserving lyric accuracy, musical alignment, complete timeline coverage, and the original master audio.

Core Features & Use Cases

  • Audio and Timeline Direction: Inspect song structure, refine lyric timings, classify instrumental gaps, and build coverage-complete shot manifests.
  • Typography-Led Visual Production: Create visual bibles, GPT Image 2 compositions, kinetic typography, semantic word choreography, and Gemini Omni Flash reference-to-video animations.
  • Adaptive Quality Control: Verify spelling, legibility, synchronization, provenance, transitions, black frames, freezes, duration, and master-audio integrity, with localized deterministic repairs when generated text fails.
  • Use Case: Produce a full lyric video for a released song with evolving chorus treatments, wordless instrumental narratives, exact lyric overlays, and a final FFmpeg assembly using only the untouched source soundtrack.

Quick Start

Use the lyric-video-director skill with the song file, exact lyrics, and rough line timings to analyze the audio, design the visual direction, generate and verify the video, and deliver a synchronized master.

Frequently Asked Questions about lyric-video-director

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a synchronized lyric video from an audio file and exact text?

To create a synchronized lyric video, you need the original master audio, exact lyrics, and rough line timings. The skill refines timings, applies kinetic typography, and assembles the final video using FFmpeg.

What is the best way to automate kinetic typography for a full song?

Automating kinetic typography involves analyzing audio structure, classifying instrumental gaps, and building a shot manifest. The skill directs semantic word choreography and reference-to-video animations to produce polished visual bibles.

Do I need FFmpeg and FFprobe to generate music videos with exact lyric overlays?

Yes, FFmpeg and FFprobe are required dependencies for generating music videos with exact lyric overlays. They inspect song structure, validate the timeline, verify duration, and assemble the final video using the untouched source soundtrack.

Can I fix spelling and synchronization errors automatically during lyric video production?

Spelling and synchronization errors can be fixed through adaptive quality control. The skill verifies legibility, provenance, and master-audio integrity, applying localized deterministic repairs when generated text fails.

How do I handle instrumental sections in a kinetic typography video?

Instrumental sections are handled by classifying instrumental gaps and creating wordless instrumental narratives. The skill builds coverage-complete shot manifests to ensure visual continuity across the entire song timeline.

What are the limitations of using automated lyric video direction for complex songs?

Automated lyric video direction requires Python, FFmpeg, and specific video generation tools. It relies on exact lyrics and rough timings provided beforehand, and may need localized deterministic repairs if generated text or transitions fail quality checks.