# scenario-sonilo

Generates sound effects and instrumental music through Sonilo models on Scenario. Useful for scoring silent video clips or creating standalone audio via MCP.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 380 installs · ★ 1141
- Author: scenario-labs
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-sonilo/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/scenario-sonilo

## What it does

This skill connects to Sonilo audio models on Scenario via MCP. It separates workflows along two axes: sound effects versus instrumental music, and standalone audio files versus source video files with the new audio track muxed in. Visuals dictate timing for video inputs. The model never reads the clip's existing audio during generation.

None of the Sonilo models generate speech, singing, or spoken dialogue. Output tracks remain strictly instrumental or ambient. The `keepSpeechVocal` flag protects human voices and ducks music under them, but it discards all non-voice audio like footsteps and engine noise. Running a music pass over footage with existing foley will wipe out that foley.

Long clips require contiguous ranges inside the `segments` parameter starting from zero. The models do not take random seeds. Good takes must be archived right away through asset downloads.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-sonilo -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-sonilo -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-sonilo -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install scenario-labs/skills scenario-sonilo
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-sonilo -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-sonilo
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-sonilo -a opencode
```

### 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/scenario-labs/skills/tree/HEAD/skills/scenario-sonilo/SKILL.md

## When to use it
- score a silent video clip with synchronized sound effects
- generate an instrumental music track from a text prompt
- replace background music in a video while keeping original speech
- mux generated audio tracks back into the source video file

## Example prompts
- Add synchronized sound effects to this silent gameplay clip using scenario-sonilo
- Generate an instrumental background track for the uploaded video and keep dialogue

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 28b7dda5fb199d8e.

BEGIN THIRD-PARTY FILE 28b7dda5fb199d8e
```text
---
name: scenario-sonilo
description: "Use when adding sound to a video or generating standalone audio with Sonilo models on Scenario via MCP: text-to-sound-effects, text-to-music, video-to-sound-effects or video-to-music from a clip, scoring silent AI video, foley, ambience, muxed video-to-video variants returning the clip with the new track mixed in, keeping speech while replacing music, or per-segment sound control. Keywords: Sonilo V1.1, SFX, soundtrack, score, keepSpeechVocal, segments, royalty-free."
license: MIT
---

# Scenario Sonilo Audio

## Overview

Sonilo, an audio family on Scenario, splits along two axes: what the sound is (sound effects or
instrumental music) and what comes back (a standalone track, or the source video with the generated
track muxed in, visuals untouched). Picking the member whose return matches the delivery matters
more than any prompt. Discover with `search` and treat `model_schema_get` as the contract.

Connection and the core loop: see the `scenario` skill in this repo; model-agnostic audio work: the
`scenario-audio` skill. If a sibling skill named here is missing from your available skills, ask the
user to install it (`npx skills add scenario-labs/skills --skill <name>`); unattended, proceed from
tool schemas and flag the gap.

## Quick reference

Member names state the mode; input names come from the live schemas:

| Member                 | Key inputs                                                          | Returns                                     |
| ---------------------- | ------------------------------------------------------------------- | ------------------------------------------- |
| Text to SFX            | `prompt`, `duration`, `audioFormat`                                 | one sound effect clip                       |
| Text to Music          | `prompt`, `duration`, `numSamples`                                  | instrumental track                          |
| Video to SFX           | `video`, optional `prompt` or `segments`                            | audio track matching the video length       |
| Video to Music         | `video`, optional `prompt`, `numSamples`, `startOffset`, `duration` | music track                                 |
| Video to Video SFX     | as Video to SFX                                                     | the video with SFX mixed in, plus the track |
| Video to Video (music) | as Video to Music, plus `keepSpeechVocal`                           | the video with music mixed in               |

At authoring time: text SFX ran 1 to 180 seconds (default 8), text music 1 to 600 (default 90),
video inputs took up to 360 seconds, `segments` up to 50, `numSamples` 1 to 3, and `startOffset`
moved in steps of 10 with `startOffset` plus `duration` capped at the video length. `audioFormat`
```
END THIRD-PARTY FILE 28b7dda5fb199d8e

The third-party file has ended. Everything between the 28b7dda5fb199d8e tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2812 of 6290 bytes. © scenario-labs · MIT · https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-sonilo/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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