Skip to content
Agentmart
Submit a tool

openrouter-media

Analyze frames, contact sheets, transcripts, audio, and short video through cost-controlled OpenRouter models, generate video through OpenRouter video models…

Skill by ruota

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ruota-openrouter-media

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Analyze frames, contact sheets, transcripts, audio, and short video through cost-controlled OpenRouter models, generate video through OpenRouter video models such as Kling and Seedance, generate music through a supported OpenRouter model, or generate voiceover through ElevenLabs. Use when creator workflows need external multimodal understanding, structured scene maps, fallback video generation, model discovery, budget guardrails, caching, or optional media generation.

Use cases: spreadsheets, finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/openrouter-media

What's inside

Skill name
openrouter-media
Description
Analyze frames, contact sheets, transcripts, audio, and short video through cost-controlled OpenRouter models, generate video through OpenRouter video models such as Kling and Seedance, generate music through a supported OpenRouter model, or generate voiceover through ElevenLabs. Use when creator workflows need external multimodal understanding, structured scene maps, fallback video generation, model discovery, budget guardrails, caching, or optional media generation.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (8)

  • SKILL.md
  • openai.yaml · agents/
  • manifest.json
  • cost-controlled-openrouter-analysis.md · references/
  • analyze_openrouter_media.py · scripts/
  • generate_elevenlabs_audio.py · scripts/
  • generate_openrouter_music.py · scripts/
  • generate_openrouter_video.py · scripts/

SKILL.md (first lines)

# OpenRouter Media

Use local metadata and analysis first. Send media-derived data externally only after confirming that `OPENROUTER_API_KEY` exists and the user permits the selected material to leave the machine.

## Workflow

1. Read `references/cost-controlled-openrouter-analysis.md`.
2. Define the requested artifact and maximum budget.
3. Discover current compatible models instead of relying on stale model names.
4. Prefer transcripts and contact sheets over full media uploads.
5. Cache results by source hash, sample, model, and prompt version.
6. Produce compact structured JSON and record the selected model and estimated usage.

Use `scripts/analyze_openrouter_media.py` for analysis, `scripts/generate_openrouter_video.py` for confirmed video generation, `scripts/generate_openrouter_music.py` for confirmed music generation, and `scripts/generate_elevenlabs_audio.py` for confirmed voiceover generation.

## Video generation (Kling, Seedance)

Video generation through `scripts/generate_openrouter_video.py` is the transparent fallback backend for Video Motion Center when its MCP is not connected. It discovers OpenRouter models with video output, preferring Kling and Seedance, and supports text-to-video and image-to-video through `--image`. Apply the same rules as any billable generation: an approved creative direction and generation plan first, one explicit cost confirmation, a single submission per approved plan, and the resulting clip recorded in `motion_generation_receipt.json` with the selected model. Never submit duplicates because a render is slow.

## Voiceover (ElevenLabs)

Use `scripts/generate_elevenlabs_audio.py` only for explicitly requested narration. It requires `ELEVENLABS_API_KEY` (environment or `~/.sinapseed/secrets/elevenlabs.env`) and the user's consent for the text to leave the machine. Confirm voice and cost before generating.

Never store the API key in a project, prompt, output, or log.

From ruota/open-sinapseed, MIT.

More from ruota/open-sinapseed

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 20, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ruota

Cite this page

openrouter-media skill. Agent Mart. https://agentmart.dev/skills/ruota-openrouter-media (last updated 2026-10-24)