[Integrations](https://spiral.ai/integrations) › [n8n](https://spiral.ai/integrations/n8n) › [Audio Understanding](https://spiral.ai/integrations/n8n/audio-understanding)

# How to Use Audio Understanding in n8n

Audio Understanding answers questions about recorded audio, such as what a discussion covers. It returns a written analysis guided by your question, with an option to request more detail.

|  |  |
| --- | --- |
| Model | Audio Understanding |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.156 per run at the default inputs for 60 seconds of input. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Audio Understanding in n8n

- Every weekday, use Audio Understanding on new meeting recordings in my recording feed. Ask what each meeting covers and prepare a morning digest.
- Each Friday, use Audio Understanding on new customer interview recordings. Request detailed analysis of the problems discussed and compile draft research notes for review.
- Every evening, use Audio Understanding on new voice memos in my recording feed. Propose a title and topic category for each memo.
- Once a week, use Audio Understanding on newly published recordings in my podcast feed. Ask for each episode's central topic and prepare a listening shortlist.
- Each morning, use Audio Understanding on new support call recordings. Ask what issue each caller reports and prepare ticket summaries for a person to check.

## How to set up Audio Understanding 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 Audio Understanding in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Audio Understanding, 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 Audio Understanding**: 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/audio-understanding",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3",
      "prompt": "What is being discussed in this audio?"
    }
  }'
```

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

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

## Audio Understanding tools and prices

- [Audio Understanding](https://spiral.ai/tools/fal/fal-ai/audio-understanding) (fal): $0.013 per 5 seconds.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| detailed_analysis |  | false | Whether to request a more detailed analysis of the audio |

## What can you do with Audio Understanding in n8n?

Prepare recurring briefs from new recordings with Audio Understanding. Have a scheduled agent ask the same focused question each time and collect the responses for review.

### Meeting briefs

Ask what a recorded meeting covers, then draft a short brief for someone who missed it.

### Customer interview review

Ask which problems a customer describes and organize the answer into research notes.

### Podcast descriptions

Ask for the central topic of a podcast recording before drafting its episode description.

### Lecture review questions

Ask which ideas a recorded lecture explains, then draft questions for reviewing those ideas.

### Support call triage

Ask what issue a caller reports and use the answer to prepare a ticket summary for review.

### Voice memo organization

Ask what each memo concerns before proposing a descriptive title and topic category.

## Overview

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

## Audio Understanding in other agents

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

## More n8n guides

- [Async Pro 1.0](https://spiral.ai/integrations/n8n/async-pro-1-0)
- [Canary Speech-to-Text](https://spiral.ai/integrations/n8n/canary-speech-to-text)
- [ACE-Step Prompt to Audio](https://spiral.ai/integrations/n8n/ace-step-prompt-to-audio)
- [Canary Speech-to-Text Turbo](https://spiral.ai/integrations/n8n/canary-speech-to-text-turbo)
- [ACE-Step Lyrics to Audio](https://spiral.ai/integrations/n8n/ace-step-lyrics-to-audio)
- [CassetteAI Music Generator](https://spiral.ai/integrations/n8n/cassetteai-music-generator)

## Questions about Audio Understanding in n8n

**Can n8n use Audio Understanding?**

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

**How much does Audio Understanding cost in n8n?**

Up to $0.156 per run at the default inputs for 60 seconds of input. 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 Audio Understanding in n8n?**

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

**How long does it take to set up Audio Understanding in n8n?**

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

**Does n8n wait while Audio Understanding runs?**

Audio Understanding runs in the background. n8n starts the run, checks on it and gives you the json when it's ready.

**What is Audio Understanding useful for?**

It answers questions about what happens in a recording. Try asking what a meeting covers, which problem a customer describes, or how a speaker explains a topic.

**What does Audio Understanding return?**

It returns written analysis based on your question. Use that response as the starting point for notes, a recording description, or a review checklist.

**How should I phrase a question about a recording?**

Ask one concrete question and specify the answer format. For example: identify the main customer complaint, then summarize it in two sentences.

**When should I request more detailed analysis?**

Request more detail when you want an explanation rather than a brief overview. Pair that request with a focus, such as the reasons given for a decision.

**Does Audio Understanding produce an audio response?**

The documented output is a text string containing the analysis. Plan to use the written response in your workflow.

