# gemini-omni

A skill for Claude Code and Codex that generates short clips via gemini-omni-1.1-flash and edits them through follow-up prompts without re-generating. Each generation returns an interaction_id so the next call changes only what you specify.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 78316 repo stars
- Author: calesthio
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/calesthio/OpenMontage/tree/HEAD/.agents/skills/gemini-omni/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/gemini-omni

## What it does

The skill runs on Claude Code and Codex through the `gemini_omni_video` tool, which calls the Gemini Interactions API directly with no gateway in between. Output is 3–10 second clips at 720p with synthesized audio, on-screen text, and scenes timed via bracketed ranges like `[0-3s]`.

Within the OpenMontage toolkit, the differentiator is stateful editing. A generation call returns `interaction_id`; passing it as `previous_interaction_id` on the next call patches the clip in place. Keep edit prompts short and surgical — a descriptive scene prompt rewrites the whole clip. Routes through fal.ai or Runway do not carry Google's interaction state, so conversational editing only works through the direct `gemini_omni_video` call.

The skill reads `GEMINI_API_KEY` or `GOOGLE_API_KEY` from the project environment, the same key used by `google_imagen` and `google_tts`. Output video is billed at $17.50 per million tokens, roughly $0.10 per second; when usage data is unavailable, the adapter falls back to a maximum 10-second estimate. Reference images go in `reference_image_paths` and are bound to roles in the prompt via `<IMAGE_REF_0>`, `<IMAGE_REF_1>`, etc.; `<FIRST_FRAME>` pins an image as the opening frame. No seed support means generations are not reproducible.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/OpenMontage --skill gemini-omni -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/gemini-omni/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/gemini-omni/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/OpenMontage --skill gemini-omni -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/gemini-omni/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/OpenMontage --skill gemini-omni -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/gemini-omni/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/OpenMontage .agents/skills/gemini-omni
```

2. **Manually: put the files in place**
- File: `.github/skills/gemini-omni/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/OpenMontage --skill gemini-omni -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/OpenMontage --path .agents/skills/gemini-omni
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/gemini-omni/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/OpenMontage/tree/HEAD/.agents/skills/gemini-omni/SKILL.md

## When to use it
- edit a generated clip in place without re-running the full generation
- generate a clip with synthesized audio and timed on-screen text
- bind a reference image to a character or style using prompt tags
- schedule scene changes across a single prompt with timecodes
- restyle or remove an object from an existing uploaded video

## Example prompts
- Generate a 5-second clip: tabby cat on a sunny windowsill, tail twitching slowly, soft background music
- Remove the phone from her hand, keep everything else — pass `previous_interaction_id` from the last response
- Start from `<FIRST_FRAME>` using `hero.jpg`: woman walking, `[0-3s]` she pauses, `[3-6s]` turns around

## Similar
- [scenario-gemini-omni](https://affpapa.org/en/nevibecode/skills/scenario-gemini-omni.md) — skill · 845 installs
- [gemini-omni-flash-api](https://affpapa.org/en/nevibecode/skills/gemini-omni-flash-api.md) — skill · 2500 installs
- [anycap-gemini-omni-video-edit](https://affpapa.org/en/nevibecode/skills/anycap-gemini-omni-video-edit.md) — skill · 517 installs
- [google-gemini-omni-video](https://affpapa.org/en/nevibecode/skills/google-gemini-omni-video.md) — skill · 144 installs
- [gemini-mcp](https://affpapa.org/en/nevibecode/mcp/gemini-mcp.md) — MCP server · ★ 225 repo stars
- [Gemini Media](https://affpapa.org/en/nevibecode/mcp/gemini-media.md) — MCP server · ★ 14 repo stars

From the same set: [calesthio/openmontage](https://affpapa.org/en/nevibecode/by/calesthio/openmontage.md) — 101 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
