# Chatterbox

Generate speech, music and audio with Chatterbox from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: audio
- Tool id: `fal` / `fal-ai/chatterbox/text-to-speech/multilingual`
- Page: https://spiral.ai/tools/fal/fal-ai/chatterbox/text-to-speech/multilingual

## Pricing

Each item in `text` adds $0.0325.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 255 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `text` (required) | text |  | — | The text to be converted to speech (maximum 300 characters). Supports 23 languages including English, French, German, Spanish, Italian, Portuguese, Hindi, Arabic, Chinese, Japanese, Korean, and more. |
| `voice` | text |  | english | Language code for synthesis. In case using custom please provide audio url and select custom_audio_language. |
| `custom_audio_language` | one of | english, arabic, danish, german, greek, spanish, finnish, french, hebrew, hindi, italian, japanese, korean, malay, dutch, norwegian, polish, portuguese, russian, swedish, swahili, turkish, chinese | — | If using a custom audio URL, specify the language of the audio here. Ignored if voice is not a custom url. |
| `exaggeration` | number | 0.25 to 2 | 0.5 | Controls speech expressiveness and emotional intensity (0.25-2.0). 0.5 is neutral, higher values increase expressiveness. Extreme values may be unstable. |
| `temperature` | number | 0.05 to 2 | 0.8 | Controls randomness and variation in generation (0.05-2.0). Higher values create more varied speech patterns. |
| `cfg_scale` | number | 0 to 1 | 0.5 | Configuration/pace weight controlling generation guidance (0.0-1.0). Use 0.0 for language transfer to mitigate accent inheritance. |
| `seed` | number (whole) |  | — | Random seed for reproducible results. Set to 0 for random generation, or provide a specific number for consistent outputs. |

## Example

```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/text-to-speech/multilingual",
    "input": {
      "text": "Last month, we reached a new milestone with two billion views on our YouTube channel."
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Fchatterbox%2Ftext-to-speech%2Fmultilingual

## Common questions

### Chatterbox

**How much does Chatterbox cost?**

Each item in `text` adds $0.0325. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Chatterbox through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/chatterbox/text-to-speech/multilingual"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Chatterbox?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Chatterbox?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

