Lyric Video Director: skill pack for Hermes Agent

Hermes Agent skill for directing typography-led lyric videos from a song, exact lyrics and line timings

What Lyric Video Director does

Lyric Video Director is a SKILL.md-based skill that Hermes discovers from its skills directory, together with the reference documents, helper scripts and templates in the repository. The workflow starts with audio inspection, structure analysis and a timeline that covers the whole song. It builds a visual bible and tracer sequences before spending on bulk generation, then uses GPT Image 2 to design compositions where the lyric text is the focus and Gemini Omni Flash to animate them through reference-to-video.

Quality control is deterministic. The skill verifies that rendered text matches the lyrics exactly, repairs failures with localized fallbacks, and assembles the final video with FFmpeg against the original master song. Audio generated by the video model is discarded. The repository also includes references for wordless instrumental narratives and non-lyric retrofit workflows, plus two helper scripts, inspect_audio.py and validate_timeline.py.

Key features

Audio inspection, structure analysis and coverage-complete timelines
Visual bibles and tracer sequences before bulk generation
Kinetic typography and semantic word-object choreography
Wordless instrumental narratives with causal transitions
Exact-text verification with localized fallback repairs
FFmpeg assembly against the untouched master audio

When to use it

Making a lyric video from a finished song, its lyrics and rough line timings
Producing a wordless visual narrative for an instrumental track
Checking a video timeline with the validate_timeline.py script

Who it is for: Musicians and video creators who run Hermes Agent and want an agent-driven workflow for typography-based lyric videos.

How it fits with Hermes Agent

Built as a Hermes Agent skill that is cloned into a Hermes profile's skills directory and discovered through its SKILL.md.

How to install Lyric Video Director

These commands are copied from the project's README. Check the repository for the latest steps before you run them.

mkdir -p ~/.hermes/profiles/<profile>/skills/creative
git clone https://github.com/ShadoW-Shinigami/lyric-video-director.git \
  ~/.hermes/profiles/<profile>/skills/creative/lyric-video-director

Requirements: Python 3, ffmpeg and ffprobe, GPT Image 2 image generation, FAL Gemini Omni Flash reference-to-video tools; optional songsee for visual audio analysis

FAQ

What is Lyric Video Director?

Lyric Video Director is a Hermes Agent skill for producing stylized lyric videos. It takes a song, exact lyrics and rough line timings, then generates typography-led visuals, animates them and checks that the text and audio are preserved.

How do I install Lyric Video Director?

Clone the repository into your Hermes profile's skills directory, for example ~/.hermes/profiles/<profile>/skills/creative/lyric-video-director. Replace <profile> with your active profile, such as telegram.

What do I need to run Lyric Video Director?

You need Python 3, ffmpeg and ffprobe, access to GPT Image 2 image generation, and FAL Gemini Omni Flash reference-to-video tools. The songsee tool is optional and adds visual audio analysis.