[Integrations](https://spiral.ai/integrations) › [Factory Droid](https://spiral.ai/integrations/factory-droid) › [Chatterbox Speech to Speech](https://spiral.ai/integrations/factory-droid/chatterbox-speech-to-speech)

# How to Use Chatterbox Speech to Speech in Factory Droid

Chatterbox Speech to Speech converts recorded speech into a reference voice for narration and character tests. It works from a spoken take, so record the wording you want before converting.

|  |  |
| --- | --- |
| Model | Chatterbox Speech to Speech |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.0195 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 Chatterbox Speech to Speech in Factory Droid

- Use Chatterbox Speech to Speech to convert the recorded tutorial narration in this project with the approved narrator reference. Save a separate result beside the original for review.
- Use Chatterbox Speech to Speech to audition the game's recorded opening line with each approved character voice reference. Label the results by character.
- Use Chatterbox Speech to Speech on one recorded product walkthrough excerpt with both narrator references in the project. Keep the same source take for both comparisons.
- Use Chatterbox Speech to Speech to convert the recorded NPC greeting with its assigned voice reference. Add the converted take to the scene's audio assets for auditioning.
- Prepare a voice audition with Chatterbox Speech to Speech using the project's recorded dialogue. Trim each target voice reference to its clearest opening 10 seconds before converting.

## How to set up Chatterbox Speech to Speech in Factory Droid

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

### Use Spiral's MCP server

1. **Add the server**: Droid saves it to your user config, `~/.factory/mcp.json`, so it works in every project.

```bash
droid mcp add spiral https://api.spiral.ai/mcp --type http
```

2. **Sign in**: Start `droid`, type `/mcp`, select spiral and authenticate it. Sign in to Spiral in the browser and click Authorize. No API key.

3. **Check it**: Spiral shows as connected. needs authentication means the sign-in did not finish: run `/mcp` again.

```bash
droid mcp list
```

### Use the Spiral skill

1. **Send Factory Droid 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 Chatterbox Speech to Speech**: 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/chatterbox/speech-to-speech",
    "input": {
      "source_audio_url": "https://storage.googleapis.com/chatterbox-demo-samples/samples/duff_stewie.wav"
    }
  }'
```

Then paste one of the prompts above: Factory Droid finds Chatterbox Speech to Speech on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/factory-droid

## Chatterbox Speech to Speech tools and prices

- [Chatterbox · Speech to Speech](https://spiral.ai/tools/fal/fal-ai/chatterbox/speech-to-speech) (fal): $0.0195 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| target_voice_audio_url |  | — | Required URL to an audio file to use as the target reference voice for speech-to-speech voice conversion. |

## What can you do with Chatterbox Speech to Speech in Factory Droid?

Create alternate voices for recorded game dialogue, walkthroughs, and other project audio with Chatterbox Speech to Speech. Your coding agent can organize the conversions and place the results beside the source recordings for review.

### Character voice auditions

Convert the same recorded line using several target voice references, then compare which vocal identity fits the character.

### Game dialogue prototypes

Turn recorded placeholder dialogue into character voice tests before choosing the voices for a playable scene.

### Narration restyling

Try a different narrator's vocal character on an existing spoken passage while keeping the recorded wording.

### Creator video voiceovers

Convert a recorded voiceover into a chosen reference voice, then audition the result against the video.

### Product demo narration

Test alternate voices for a recorded product walkthrough before selecting the narration for the edit.

### Voice direction comparisons

Hold the source recording constant and change only the target voice reference to compare vocal identities on the same material.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Factory Droid guides](https://spiral.ai/integrations/factory-droid)

## Chatterbox Speech to Speech in other agents

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

## More Factory Droid guides

- [Chatterbox Multilingual](https://spiral.ai/integrations/factory-droid/chatterbox-multilingual)
- [Chatterbox TTS](https://spiral.ai/integrations/factory-droid/chatterbox-tts)
- [Chatterbox HD Speech to Speech](https://spiral.ai/integrations/factory-droid/chatterbox-hd-speech-to-speech)
- [Cohere Transcribe](https://spiral.ai/integrations/factory-droid/cohere-transcribe)
- [Chatterbox HD](https://spiral.ai/integrations/factory-droid/chatterbox-hd)
- [DeepFilterNet 3](https://spiral.ai/integrations/factory-droid/deepfilternet-3)

## Questions about Chatterbox Speech to Speech in Factory Droid

**Can Factory Droid use Chatterbox Speech to Speech?**

Yes. Add Spiral to Factory Droid as an MCP server, and Factory Droid can find and run Chatterbox Speech to Speech like any built-in tool.

**How much does Chatterbox Speech to Speech cost in Factory Droid?**

Up to $0.0195 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 Factory Droid plan is separate.

**Do I need a fal account to use Chatterbox Speech to Speech in Factory Droid?**

No. Spiral runs Chatterbox Speech to Speech on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Chatterbox Speech to Speech in Factory Droid?**

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

**Does Factory Droid wait while Chatterbox Speech to Speech runs?**

Chatterbox Speech to Speech runs in the background. Factory Droid starts the run, checks on it and gives you the audio when it's ready.

**What is Chatterbox Speech to Speech good for?**

Use it to try a different vocal identity on an existing spoken recording. Practical uses include character auditions, narration restyling, and alternate voiceovers for creator videos.

**Can Chatterbox Speech to Speech rewrite what I said?**

Its conversion path works from recorded speech and is intended to preserve the spoken content. Record a revised take first when you need different wording.

**How long should the target voice reference be?**

Put the useful voice sample within the first 10 seconds. The maker's implementation truncates the reference there, so extra speech after that point does not provide additional guidance.

**What improves voice-conversion quality?**

Start with clear source speech and a clean target voice recording. If a conversion sounds poor, compare cleaner recordings before processing more material.

**Does Chatterbox watermark converted speech?**

The maker's conversion code applies PerTh watermarking before returning the recording. The model card describes the watermark as imperceptible.

