[Integrations](https://spiral.ai/integrations) › [Windsurf](https://spiral.ai/integrations/windsurf) › [ElevenLabs Audio Isolation](https://spiral.ai/integrations/windsurf/elevenlabs-audio-isolation)

# How to Use ElevenLabs Audio Isolation in Windsurf

ElevenLabs Audio Isolation cleans spoken dialogue for podcasts, interviews, and film by removing background noise and music. Its focus is speech cleanup; ElevenLabs says it is not specifically optimized for extracting singing from songs.

|  |  |
| --- | --- |
| Model | ElevenLabs Audio Isolation |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.13 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 ElevenLabs Audio Isolation in Windsurf

- Use ElevenLabs Audio Isolation to clean assets/audio/interview.mp3. Save the processed track beside the original with a clear filename for listening review.
- Process the 20-minute podcast recording in this project with ElevenLabs Audio Isolation. Keep the original and place the cleaned dialogue in the editing assets directory.
- Use ElevenLabs Audio Isolation on the noisy narration asset, then pass the cleaned speech to our existing transcription tool. Save both outputs for review.
- Clean the speech in our 90-second demo recording with ElevenLabs Audio Isolation. Add the resulting audio to the project as an alternative track for the video edit.
- Use ElevenLabs Audio Isolation to prepare the recorded voice sample in this project before our separate voice changer step. Save the cleaned intermediate audio.

## How to set up ElevenLabs Audio Isolation in Windsurf

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

### Use Spiral's MCP server

1. **Add the server**: Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: `~/.config/devin/mcp_config.json` on macOS and Linux, `%APPDATA%\devin\mcp_config.json` on Windows. Add this:

```json
{
  "mcpServers": {
    "spiral": {
      "url": "https://api.spiral.ai/mcp"
    }
  }
}
```

2. **Sign in**: Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.

```bash
devin mcp login spiral
```

3. **Check it**: Spiral is listed under This computer in Customize › MCPs. From the terminal:

```bash
devin mcp list
```

### Use the Spiral skill

1. **Send Windsurf 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 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 ElevenLabs Audio Isolation**: 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/elevenlabs/audio-isolation",
    "input": {
      "audio_url": "https://v3.fal.media/files/zebra/zJL_oRY8h5RWwjoK1w7tx_output.mp3"
    }
  }'
```

Then paste one of the prompts above: Windsurf finds ElevenLabs Audio Isolation on Spiral, shows the price and runs it.

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

## ElevenLabs Audio Isolation tools and prices

- [ElevenLabs Audio Isolation](https://spiral.ai/tools/fal/fal-ai/elevenlabs/audio-isolation) (fal): $0.13 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| audio_url |  | — | URL of the audio file to isolate voice from |
| video_url |  | — | Video file to use for audio isolation. Either `audio_url` or `video_url` must be provided. |

## What can you do with ElevenLabs Audio Isolation in Windsurf?

Prepare cleaner dialogue assets for your project's podcast, interview, or video edits. Use ElevenLabs Audio Isolation before a separate transcription or voice transformation step when the source recording has background interference.

### Podcast dialogue cleanup

Use ElevenLabs Audio Isolation to reduce background noise in a recorded podcast before editing the conversation.

### Interview postproduction

Clean a noisy interview with ElevenLabs Audio Isolation and keep the original alongside the processed track for review.

### Film dialogue preparation

Use ElevenLabs Audio Isolation to extract spoken dialogue from a mixed soundtrack for a film edit.

### Meeting recording cleanup

Reduce background interference in a recorded meeting with ElevenLabs Audio Isolation before sharing the listening copy.

### Speech over background music

Use ElevenLabs Audio Isolation on a spoken clip with music underneath to prepare a dialogue track for editing.

### Transcription preparation

Run noisy speech through ElevenLabs Audio Isolation, then send the cleaned recording to a separate transcription model.

### Voice transformation preparation

Use ElevenLabs Audio Isolation to clean the source speech before a separate voice changer processes it.

### Video dialogue replacement

Prepare cleaned dialogue with ElevenLabs Audio Isolation, then use that audio to replace the original track in a video editor.

## Overview

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

## ElevenLabs Audio Isolation in other agents

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

## More Windsurf guides

- [Eleven v4 Turbo](https://spiral.ai/integrations/windsurf/eleven-v4-turbo)
- [ElevenLabs Dubbing v2](https://spiral.ai/integrations/windsurf/elevenlabs-dubbing-v2)
- [Eleven v4](https://spiral.ai/integrations/windsurf/eleven-v4)
- [ElevenLabs English Voice Changer v2](https://spiral.ai/integrations/windsurf/elevenlabs-english-voice-changer-v2)
- [Eleven v3 Conversational](https://spiral.ai/integrations/windsurf/eleven-v3-conversational)
- [ElevenLabs Forced Alignment](https://spiral.ai/integrations/windsurf/elevenlabs-forced-alignment)

## Questions about ElevenLabs Audio Isolation in Windsurf

**Can Windsurf use ElevenLabs Audio Isolation?**

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

**How much does ElevenLabs Audio Isolation cost in Windsurf?**

Up to $0.13 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 Windsurf plan is separate.

**Do I need a fal account to use ElevenLabs Audio Isolation in Windsurf?**

No. Spiral runs ElevenLabs Audio Isolation on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up ElevenLabs Audio Isolation in Windsurf?**

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

**Does Windsurf wait while ElevenLabs Audio Isolation runs?**

ElevenLabs Audio Isolation runs in the background. Windsurf starts the run, checks on it and gives you the audio when it's ready.

**What is ElevenLabs Audio Isolation best for?**

Cleaning spoken recordings for podcast, interview, and film editing. It removes background interference around the dialogue.

**Can it remove music underneath speech?**

Yes. ElevenLabs documents removing background music, chatter, and ambient interference from spoken recordings.

**Can it extract a singer's vocals from a song?**

It may work on some recordings, but ElevenLabs says it is not specifically optimized for isolating singing from music. Test a short excerpt before using it for a full song.

**How long can a recording be?**

ElevenLabs documents limits of one hour and 500 MB. Keep each recording within both limits.

**What audio format does it produce?**

ElevenLabs documents MP3 as the default output for audio isolation.

