[Integrations](https://spiral.ai/integrations) › [n8n](https://spiral.ai/integrations/n8n) › [MMAudio V2](https://spiral.ai/integrations/n8n/mmaudio-v2)

# How to Use MMAudio V2 in n8n

MMAudio V2 adds synchronized sound effects and ambience to existing video, using a 44.1 kHz audio model. The authors recommend V2 and report better generalization to new footage than the earlier MMAudio checkpoint.

|  |  |
| --- | --- |
| Model | MMAudio V2 |
| Available through | fal |
| Category | Video |
| Price | $0.0013 per second. Billed on `duration`, default 8. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with MMAudio V2 in n8n

- Every Monday, use MMAudio V2 to make a sound draft for each new 8-second silent nature video in my review collection. Describe the visible setting, request environmental sound without speech or music, and queue the results for review.
- Each morning, use MMAudio V2 on new 8-second product handling videos in my collection. Request sounds for the visible materials and actions, and include the sound description beside each result.
- Every Friday, use MMAudio V2 to prepare two sound interpretations of each new 8-second outdoor shot in my review collection. Keep one subdued and one more active, and leave both for me to compare.
- Each evening, use MMAudio V2 on new 8-second dog clips in my review collection. Request barking and outdoor ambience without music, and flag the bark timing as something I should check.
- Every Tuesday, use MMAudio V2 for new 8-second golf practice clips in my review collection. Request a sharp strike with quiet outdoor ambience and organize the results for checking sound against ball contact.

## How to set up MMAudio V2 in n8n

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send n8n this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Create a key**: Create a key under API keys in the console.

2. **Add an MCP Client node**: In a workflow, add an MCP Client node (or, under an AI Agent node, an MCP Client Tool) and set:

```text
https://api.spiral.ai/mcp
```

3. **Pick a tool**: The node lists Spiral's tools. In an MCP Client node pick one, such as `run`, and give it its arguments:

```json
{
  "provider": "fal",
  "model": "fal-ai/flux/schnell",
  "input": { "prompt": "a lighthouse at dawn" },
  "wait": true
}
```

4. **Run MMAudio V2 in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds MMAudio V2, prices it and runs it each time the step fires.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run MMAudio V2**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/mmaudio-v2",
    "input": {
      "video_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4",
      "prompt": "Indian holy music"
    }
  }'
```

Then paste one of the prompts above: n8n finds MMAudio V2 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/n8n

## MMAudio V2 tools and prices

- [MMAudio V2 · Video to Video](https://spiral.ai/tools/fal/fal-ai/mmaudio-v2) (fal): $0.0013 per second. Billed on `duration`, default 8.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | The negative prompt to generate the audio for. |
| seed | 0 to 65535 | — | The seed for the random number generator |
| num_steps | 4 to 50 | 25 | The number of steps to generate the audio for. |
| duration | 1 to 30 | 8 | The duration of the audio to generate. |
| cfg_strength | 0 to 20 | 4.5 | The strength of Classifier Free Guidance. |
| mask_away_clip |  | false | Whether to mask away the clip. |

## What can you do with MMAudio V2 in n8n?

Prepare recurring sound-design drafts for short video collections with MMAudio V2. A scheduled agent can organize new attempts into a review queue with the intended sounds described beside each result.

### Foley for silent AI footage

Add ambience and action sounds to short generated shots. Review each result against visible movement before using it in an edit.

### Nature footage

Try environmental sound for short outdoor shots, describing the audible setting and the main visible action.

### Animal clips

Generate barking or howling for footage with visible animal activity. Check that vocalizations occur at plausible moments.

### Sports impact sounds

Add a draft sound pass to a short golf or racket-sport shot, then inspect the contact point for timing errors.

### Percussion footage

Try synchronized hits for a short drum performance. Listen for missed strikes and extra hits before keeping the result.

### Product handling videos

Prototype Foley for short shots of objects being opened, placed, or handled. Describe the materials and desired sounds as a sound-design brief.

### Sound alternatives for an edit

Generate several interpretations of the same short shot by changing the sound description. Compare ambience, prominence of effects, and synchronization.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All n8n guides](https://spiral.ai/integrations/n8n)

## MMAudio V2 in other agents

- [Amp](https://spiral.ai/integrations/amp/mmaudio-v2)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mmaudio-v2)
- [Claude](https://spiral.ai/integrations/claude-desktop/mmaudio-v2)
- [Claude Code](https://spiral.ai/integrations/claude-code/mmaudio-v2)
- [Cline](https://spiral.ai/integrations/cline/mmaudio-v2)
- [Codex](https://spiral.ai/integrations/codex/mmaudio-v2)
- [Cursor](https://spiral.ai/integrations/cursor/mmaudio-v2)
- [Devin](https://spiral.ai/integrations/devin/mmaudio-v2)
- [dots](https://spiral.ai/integrations/dots/mmaudio-v2)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mmaudio-v2)
- [Gemini](https://spiral.ai/integrations/gemini/mmaudio-v2)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mmaudio-v2)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mmaudio-v2)
- [goose](https://spiral.ai/integrations/goose/mmaudio-v2)
- [Grok](https://spiral.ai/integrations/grok/mmaudio-v2)
- [Grok Build](https://spiral.ai/integrations/grok-build/mmaudio-v2)
- [Hermes](https://spiral.ai/integrations/hermes/mmaudio-v2)
- [Instinct](https://spiral.ai/integrations/instinct/mmaudio-v2)
- [Manus](https://spiral.ai/integrations/manus/mmaudio-v2)
- [Muse](https://spiral.ai/integrations/muse/mmaudio-v2)
- [Muse Code](https://spiral.ai/integrations/muse-code/mmaudio-v2)
- [Notion](https://spiral.ai/integrations/notion/mmaudio-v2)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mmaudio-v2)
- [opencode](https://spiral.ai/integrations/opencode/mmaudio-v2)
- [Perplexity](https://spiral.ai/integrations/perplexity/mmaudio-v2)
- [Raycast](https://spiral.ai/integrations/raycast/mmaudio-v2)
- [VS Code](https://spiral.ai/integrations/vscode/mmaudio-v2)
- [Windsurf](https://spiral.ai/integrations/windsurf/mmaudio-v2)
- [Zapier](https://spiral.ai/integrations/zapier/mmaudio-v2)

## More n8n guides

- [Luma Ray 3.2 Video to Video](https://spiral.ai/integrations/n8n/luma-ray-3-2-video-to-video)
- [Marey Realism 1.5 Image to Video](https://spiral.ai/integrations/n8n/marey-realism-1-5-image-to-video)
- [Luma Ray 3.2 Text to Video](https://spiral.ai/integrations/n8n/luma-ray-3-2-text-to-video)
- [Marey Realism 1.5 Motion Transfer](https://spiral.ai/integrations/n8n/marey-realism-1-5-motion-transfer)
- [Luma Ray 3.2 Reframe](https://spiral.ai/integrations/n8n/luma-ray-3-2-reframe)
- [Marey Realism 1.5 Pose Transfer](https://spiral.ai/integrations/n8n/marey-realism-1-5-pose-transfer)

## Questions about MMAudio V2 in n8n

**Can n8n use MMAudio V2?**

Yes. Add Spiral to n8n as an MCP server, and n8n can find and run MMAudio V2 like any built-in tool.

**How much does MMAudio V2 cost in n8n?**

$0.0013 per second. Billed on `duration`, default 8. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your n8n plan is separate.

**Do I need a fal account to use MMAudio V2 in n8n?**

You need no fal account. n8n uses one Spiral API key for every tool, and Spiral runs MMAudio V2 on its own fal account.

**How long does it take to set up MMAudio V2 in n8n?**

About two minutes: create a key, then add an MCP Client node, then pick a tool.

**Does n8n wait while MMAudio V2 runs?**

MMAudio V2 runs in the background. n8n starts the run, checks on it and gives you the video when it's ready.

**What is MMAudio V2 useful for?**

Use it to add sound effects and ambience that follow visible action in existing footage. Its recommended checkpoint generates 44.1 kHz audio.

**Can MMAudio V2 generate dialogue or a musical score?**

Its focus is Foley: sound effects and ambience. Human speech requests can produce unintelligible mumbles, so use a dedicated speech or music model for those tasks.

**What clip length should I start with?**

Start with an 8-second shot, which matches the training duration. The authors warn that large departures from that length can reduce quality.

**Will a 4K source produce better sound?**

Higher source resolution does not improve the generated audio. Choose footage where the action is clear, and judge the result by listening to how the sound matches it.

**How should I prompt MMAudio V2?**

Describe the sounds you want, such as a sharp ball strike with quiet outdoor ambience. If the result follows the text too loosely, try increasing guidance strength and compare the timing again.

