[Integrations](https://spiral.ai/integrations) › [Hermes](https://spiral.ai/integrations/hermes) › [ACE-Step Audio Outpaint](https://spiral.ai/integrations/hermes/ace-step-audio-outpaint)

# How to Use ACE-Step Audio Outpaint in Hermes

ACE-Step Audio Outpaint adds an intro, outro, or continuation to existing music using style instructions and optional lyrics. Use it to lengthen a cue or develop a song sketch, then audition the join for abrupt transitions.

|  |  |
| --- | --- |
| Model | ACE-Step Audio Outpaint |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.0156 per run at the default inputs for 60 seconds of input. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with ACE-Step Audio Outpaint in Hermes

- Every Monday, use ACE-Step Audio Outpaint on the music clip attached to the weekly video brief. Add 20 seconds at the end with instrumental acoustic guitar and light percussion, then collect the result for review.
- For each new podcast episode brief with an attached theme clip, use ACE-Step Audio Outpaint to add a 10-second instrumental opening. Request warm piano and soft percussion.
- Every Friday, use ACE-Step Audio Outpaint on the attached documentary music sketch to add a 15-second instrumental ending. Request quiet strings and sparse piano, then put the result in the review queue.
- For each approved presentation brief with an attached instrumental bed, use ACE-Step Audio Outpaint to add 20 seconds after the ending. Request restrained electronic music with warm pads and light percussion.
- Each week, use ACE-Step Audio Outpaint on the attached ambient cue to prepare three 15-second continuations. Keep the musical description unchanged, use a different random seed for each, and collect all three for listening review.

## How to set up ACE-Step Audio Outpaint in Hermes

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

### Use the Spiral skill

1. **Send Hermes 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. **Add the server and sign in**: Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.

```bash
hermes mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --auth oauth \
  --connect-timeout 300
```

2. **Check it**: In a chat that was already open, run `/reload-mcp`.

```bash
hermes mcp list
hermes mcp test spiral
```

### 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 ACE-Step Audio Outpaint**: 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/ace-step/audio-outpaint",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav",
      "tags": "lofi, hiphop, drum and bass, trap, chill"
    }
  }'
```

Then paste one of the prompts above: Hermes finds ACE-Step Audio Outpaint on Spiral, shows the price and runs it.

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

## ACE-Step Audio Outpaint tools and prices

- [ACE Step Extend · Audio Outpaint](https://spiral.ai/tools/fal/fal-ai/ace-step/audio-outpaint) (fal): $0.00026 per second.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| extend_before_duration | 0 to 107 | 0 | Duration in seconds to extend the audio from the start. |
| extend_after_duration | 0 to 107 | 30 | Duration in seconds to extend the audio from the end. |
| lyrics |  |  | Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song. |
| number_of_steps | 3 to 60 | 27 | Number of steps to generate the audio. |
| seed |  | — | Random seed for reproducibility. If not provided, a random seed will be used. |
| scheduler | euler, heun | euler | Scheduler to use for the generation process. |

## What can you do with ACE-Step Audio Outpaint in Hermes?

Prepare longer music cues for recurring videos, podcast episodes, or presentations. A scheduled agent can apply a consistent musical brief to each source clip and collect the results for listening review.

### Longer video music cues

Extend an existing instrumental cue to cover an extra scene. Describe the instruments and mood you want in the added section.

### Podcast opening music

Add a short instrumental lead-in before an existing theme so the host has room for an opening line.

### Closing credits music

Add an outro to an existing score sketch. Request a quieter arrangement for the credits and review the result against the edit.

### Songwriting continuations

Continue a recorded song sketch with a proposed verse or chorus. Supply the new lyrics and audition the musical direction.

### Game scene music drafts

Lengthen an existing ambient cue for a menu, exploration scene, or dialogue sequence. Review the continuation in the game before accepting it.

### Presentation background music

Extend an existing instrumental bed to cover another slide sequence or a longer product demonstration.

### Alternate musical endings

Generate several continuations from the same source and brief, changing the random seed between attempts. Compare the endings before choosing one.

## Overview

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

## ACE-Step Audio Outpaint in other agents

- [Amp](https://spiral.ai/integrations/amp/ace-step-audio-outpaint)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/ace-step-audio-outpaint)
- [Claude](https://spiral.ai/integrations/claude-desktop/ace-step-audio-outpaint)
- [Claude Code](https://spiral.ai/integrations/claude-code/ace-step-audio-outpaint)
- [Cline](https://spiral.ai/integrations/cline/ace-step-audio-outpaint)
- [Codex](https://spiral.ai/integrations/codex/ace-step-audio-outpaint)
- [Cursor](https://spiral.ai/integrations/cursor/ace-step-audio-outpaint)
- [Devin](https://spiral.ai/integrations/devin/ace-step-audio-outpaint)
- [dots](https://spiral.ai/integrations/dots/ace-step-audio-outpaint)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/ace-step-audio-outpaint)
- [Gemini](https://spiral.ai/integrations/gemini/ace-step-audio-outpaint)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/ace-step-audio-outpaint)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/ace-step-audio-outpaint)
- [goose](https://spiral.ai/integrations/goose/ace-step-audio-outpaint)
- [Grok](https://spiral.ai/integrations/grok/ace-step-audio-outpaint)
- [Grok Build](https://spiral.ai/integrations/grok-build/ace-step-audio-outpaint)
- [Instinct](https://spiral.ai/integrations/instinct/ace-step-audio-outpaint)
- [Manus](https://spiral.ai/integrations/manus/ace-step-audio-outpaint)
- [Muse](https://spiral.ai/integrations/muse/ace-step-audio-outpaint)
- [Muse Code](https://spiral.ai/integrations/muse-code/ace-step-audio-outpaint)
- [n8n](https://spiral.ai/integrations/n8n/ace-step-audio-outpaint)
- [Notion](https://spiral.ai/integrations/notion/ace-step-audio-outpaint)
- [OpenClaw](https://spiral.ai/integrations/openclaw/ace-step-audio-outpaint)
- [opencode](https://spiral.ai/integrations/opencode/ace-step-audio-outpaint)
- [Perplexity](https://spiral.ai/integrations/perplexity/ace-step-audio-outpaint)
- [Raycast](https://spiral.ai/integrations/raycast/ace-step-audio-outpaint)
- [VS Code](https://spiral.ai/integrations/vscode/ace-step-audio-outpaint)
- [Windsurf](https://spiral.ai/integrations/windsurf/ace-step-audio-outpaint)
- [Zapier](https://spiral.ai/integrations/zapier/ace-step-audio-outpaint)

## More Hermes guides

- [ACE-Step Audio Inpaint](https://spiral.ai/integrations/hermes/ace-step-audio-inpaint)
- [ACE-Step Audio to Audio](https://spiral.ai/integrations/hermes/ace-step-audio-to-audio)
- [xAI](https://spiral.ai/integrations/hermes/xai)
- [ACE-Step Lyrics to Audio](https://spiral.ai/integrations/hermes/ace-step-lyrics-to-audio)
- [Vizard](https://spiral.ai/integrations/hermes/vizard)
- [ACE-Step Prompt to Audio](https://spiral.ai/integrations/hermes/ace-step-prompt-to-audio)

## Questions about ACE-Step Audio Outpaint in Hermes

**Can Hermes use ACE-Step Audio Outpaint?**

Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run ACE-Step Audio Outpaint like any built-in tool.

**How much does ACE-Step Audio Outpaint cost in Hermes?**

Up to $0.0156 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 Hermes plan is separate.

**Do I need a fal account to use ACE-Step Audio Outpaint in Hermes?**

No. Spiral runs ACE-Step Audio Outpaint on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up ACE-Step Audio Outpaint in Hermes?**

About two minutes: add the server and sign in, then check it.

**Does Hermes wait while ACE-Step Audio Outpaint runs?**

ACE-Step Audio Outpaint runs in the background. Hermes starts the run, checks on it and gives you the audio when it's ready.

**What is ACE-Step Audio Outpaint useful for?**

It adds music before or after an existing recording. Useful starting points include a longer video cue, a podcast intro, or another section of a song demo.

**How should I describe the extension?**

Give a focused musical description: genre, instruments, mood, and intended use. For example, try “ambient, soft piano, warm pads, quiet documentary ending.”

**Can I request instrumental music or sung lyrics?**

Yes. Use [inst] or [instrumental] for instrumental music, or supply lyrics with section markers such as [verse] and [chorus].

**Which languages should I try first?**

The maker lists English, Chinese, Russian, Spanish, Japanese, German, French, Portuguese, Italian, and Korean among its better-performing languages. Audition pronunciation and lyric delivery before using a vocal extension.

**Why do some attempts sound better than others?**

The model card warns that results are sensitive to random seeds and input duration. Compare a few attempts before rewriting the whole musical brief.

