uzairansaruzi
Featured
hermex
Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It combines GPT Image 2 for typography design and Gemini Omni Flash for animation with deterministic QC and exact-text verification, all while preserving the original master audio.
Who it is for
- Music video producers and editors
- Content creators and artists wanting automated lyric videos
- AI/ML developers exploring multi-model pipelines
- Musicians needing low-cost lyric video generation
Use cases
- Creating professional lyric videos for singles or albums
- Generating kinetic typography with semantic word-object choreography
- Producing wordless instrumental narratives with causal transitions
- Automating quality control with localized fallback repairs
Strengths
- Production-grade pipeline treating the lyric as protagonist
- Combines image generation, video animation, and deterministic QC
- Open-source MIT license with ready-to-use scripts and templates
- Preserves original master audio as the sole soundtrack
Considerations
- Requires access to paid APIs (GPT Image 2, Gemini Omni Flash)
- Dependent on Hermes Agent ecosystem and its setup
- Needs Python 3, ffmpeg, and optional songsee tool
- Limited to reference-to-video animation style and typography-led design
README quick start
Lyric Video Director
A production-grade Hermes Agent skill for directing stylized lyric videos from a song, exact lyrics, and rough line timings.
It treats the lyric as the protagonist: GPT Image 2 designs typography-led compositions, Gemini Omni Flash animates them through reference-to-video, and deterministic QC preserves exact text and the untouched master audio.
What it covers
- Audio inspection, structure analysis, and coverage-complete timelines
- Visual bibles and tracer sequences before expensive bulk generation
- Kinetic typography and semantic word-object choreography
- Wordless instrumental narratives with causal transitions
- Exact-text verification and localized fallback repairs
- FFmpeg assembly against the original master song
- Technical, textual, musical, and creative-parity QC
Install
Copy or clone this repository into your Hermes profile's skills directory:
mkdir -p ~/.hermes/profiles//skills/creative
git clone https://github.com/ShadoW-Shinigami/lyric-video-director.git \
~/.hermes/profiles//skills/creative/lyric-video-director
Replace `` with your active profile, such as telegram.
The main skill definition is SKILL.md. Hermes discovers its linked references, scripts, and templates from the repository layout.
Repository layout
.
├── SKILL.md
├── references/
│ ├── art-direction-and-prompts.md
│ ├── audio-and-timeline.md
│ ├── full-song-production-qc.md
│ ├── instrumental-narrative-direction.md
│ ├── kinetic-typography-reference-video.md
│ ├── non-lyric-retrofit-workflow.md
│ ├── typography-and-qc.md
│ └── worked-examples.md
├── scripts/
│ ├── inspect_audio.py
│ └── validate_timeline.py
└── templates/
├── project.yaml
└── timeline.example.json
Requirements
The skill expects access to:
- Python 3
ffmpegandffprobe- GPT Image 2 image generation
- FAL Gemini Omni Flash reference-to-video tools
- Optional:
songseefor visual audio analysis
Run the helper checks:
python3 scripts/inspect_audio.py --help
python3 scripts/validate_timeline.py --help
Core rule
The supplied song is sacred. Generated video audio is discarded, and the original master remains the sole final soundtrack.
License
MIT — see LICENSE.
Description
Hermes Agent skill for typography-led lyric videos using GPT Image 2, Gemini Omni Flash, and exact-text QC
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.