[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [ElevenLabs Voice Changer](https://spiral.ai/integrations/codex/elevenlabs-voice-changer)

# How to Use ElevenLabs Voice Changer in Codex

ElevenLabs Voice Changer recasts recorded speech in another voice while keeping the performance's emotion and timing. Use it for character dialogue, narration, and pronunciation pickups when you want to direct the delivery yourself.

|  |  |
| --- | --- |
| Model | ElevenLabs Voice Changer |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.39 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 Voice Changer in Codex

- Use ElevenLabs Voice Changer to convert the recorded dialogue in assets/dialogue into the character voice I selected. Check that every take is five minutes or less and save converted takes separately from the originals.
- Use ElevenLabs Voice Changer on the corrected pronunciation takes in audio/pickups. Save each converted phrase beside its original and prepare a list of the narration lines it should replace.
- Use ElevenLabs Voice Changer to recast the recorded tutorial narration in this project. Split recordings longer than five minutes at sentence boundaries and preserve their playback order.
- Use ElevenLabs Voice Changer on the three recorded performances in assets/auditions, using the same selected voice for each. Build a simple playback page so I can compare their emotional delivery.
- Use ElevenLabs Voice Changer to convert the next dialogue take with seed 42, keeping the other settings unchanged. Save it as another take for comparison without assuming the audio will be identical.

## How to set up ElevenLabs Voice Changer in Codex

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

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex 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 Voice Changer**: 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/voice-changer",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/elevenlabs/voice_change_in.mp3"
    }
  }'
```

Then paste one of the prompts above: Codex finds ElevenLabs Voice Changer on Spiral, shows the price and runs it.

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

## ElevenLabs Voice Changer tools and prices

- [ElevenLabs Voice Changer](https://spiral.ai/tools/fal/fal-ai/elevenlabs/voice-changer) (fal): $0.39 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| voice |  | Rachel | The voice to use for speech generation |
| remove_background_noise |  | false | If set, will remove the background noise from your audio input using our audio isolation model. |
| seed |  | — | Random seed for reproducibility. |
| output_format | mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192 | mp3_44100_128 | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. |

## What can you do with ElevenLabs Voice Changer in Codex?

Turn recorded performances into dialogue and narration assets for your project. A coding agent can organize takes, divide recordings into sections within five minutes, and prepare converted audio for review.

### Game character dialogue

Convert performed dialogue into a character voice while keeping the actor's emotional delivery. Process each recording in sections of five minutes or less.

### Animation dialogue

Record the character's delivery yourself, then recast the performance in the chosen voice. Review the converted lines against the scene before editing them in.

### Pronunciation pickups

Record a corrected word or phrase and convert it into the narration voice. Use the result as a replacement take in an existing recording.

### Educational narration

Perform a lesson with deliberate pauses and emphasis, then convert it into a consistent narrator voice. Divide longer lessons into short sections.

### Short story narration

Keep a recorded storytelling performance while changing its voice. Use separate takes to direct the emotion of individual passages.

### Dialogue across recording sessions

Convert separately recorded character lines into the same target voice. Compare the performances for matching accent and delivery before assembling the scene.

### Performed dubbing

Record dialogue in the intended language, then convert it into the desired character voice. The conversion retains the recorded language and accent.

## Overview

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

## ElevenLabs Voice Changer in other agents

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

## More Codex guides

- [ElevenLabs Turbo v2.5](https://spiral.ai/integrations/codex/elevenlabs-turbo-v2-5)
- [ElevenLabs Voice Changer Multilingual v2](https://spiral.ai/integrations/codex/elevenlabs-voice-changer-multilingual-v2)
- [ElevenLabs TTS Turbo v2.5](https://spiral.ai/integrations/codex/elevenlabs-tts-turbo-v2-5)
- [ElevenLabs Voice Isolator](https://spiral.ai/integrations/codex/elevenlabs-voice-isolator)
- [ElevenLabs Sound Effects V2](https://spiral.ai/integrations/codex/elevenlabs-sound-effects-v2)
- [ElevenLabs v4 Text to Speech](https://spiral.ai/integrations/codex/elevenlabs-v4-text-to-speech)

## Questions about ElevenLabs Voice Changer in Codex

**Can Codex use ElevenLabs Voice Changer?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run ElevenLabs Voice Changer like any built-in tool.

**How much does ElevenLabs Voice Changer cost in Codex?**

Up to $0.39 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 Codex plan is separate.

**Do I need a fal account to use ElevenLabs Voice Changer in Codex?**

No. Spiral runs ElevenLabs Voice Changer 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 Voice Changer in Codex?**

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

**Does Codex wait while ElevenLabs Voice Changer runs?**

ElevenLabs Voice Changer runs in the background. Codex starts the run, checks on it and gives you the audio when it's ready.

**What does ElevenLabs Voice Changer preserve?**

It changes the voice while preserving the recorded performance's emotional delivery and nuance. Record the pauses, emphasis, and delivery you want the result to follow.

**How long can a recording be?**

Each conversion supports up to five minutes of audio. Split longer narration into sections before converting it.

**Does ElevenLabs Voice Changer translate speech or change its accent?**

The recording's language and accent carry into the result. ElevenLabs documents 29 supported languages; perform the speech in the language and accent you want to retain.

**How should I direct emotion and pronunciation?**

Demonstrate them in the source recording. For a pronunciation correction, record the phrase as you want it spoken, then convert that performance into the target voice.

**What should I check before converting a recording?**

Listen for clipping and confirm that the accent and delivery match your goal. Conversion carries performance details forward, so correct the recording before processing it.

