# Chatterbox Multilingual

> Chatterbox open-source TTS in 23 languages with instant voice cloning and emotion exaggeration control. Max 300 characters per request.

- **Provider**: replicate
- **Model ID**: resemble-ai/chatterbox-multilingual
- **Category**: tts_voice
- **Credits**: 7 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `text` (string, **required**): Text to synthesize into speech (maximum 300 characters)
- `reference_audio` (string, optional): Reference audio file for voice cloning (optional). If not provided, uses default voice for the selected language.
- `language` (string, optional): Language for synthesis (Default: `en`; Options: `ar`, `da`, `de`, `el`, `en`, `es`, `fi`, `fr`, `he`, `hi`, `it`, `ja`, `ko`, `ms`, `nl`, `no`, `pl`, `pt`, `ru`, `sv`, `sw`, `tr`, `zh`)
- `temperature` (number, optional): Controls randomness in generation (0.05-5.0, higher=more varied) (Default: `0.8`; Range: min: 0.05, max: 5)
- `cfg_weight` (number, optional): CFG/Pace weight controlling generation guidance (0.2-1.0). Use 0.5 for balanced results, 0 for language transfer (Default: `0.5`; Range: min: 0.2, max: 1)
- `exaggeration` (number, optional): Controls speech expressiveness (0.25-2.0, neutral=0.5, extreme values may be unstable) (Default: `0.5`; Range: min: 0.25, max: 2)
- `seed` (integer, optional): Random seed for reproducible results (0 for random generation) (Default: `0`)

## Example Request

```json
{
  "model": "resemble-ai/chatterbox-multilingual",
  "input": {
    "exaggeration": 0.5,
    "seed": 0,
    "cfg_weight": 0.5,
    "temperature": 0.8,
    "language": "fr",
    "text": "Replicate est une entreprise v\u00e9ritablement impressionnante. Elle se distingue par sa capacit\u00e9 \u00e0 rendre accessibles des mod\u00e8les d\u2019intelligence artificielle puissants \u00e0 un grand nombre d\u2019utilisateurs, qu\u2019ils soient chercheurs, d\u00e9veloppeurs ou cr\u00e9ateurs.",
    "reference_audio": "https://replicate.delivery/pbxt/Nefzy5KEvtNzIKfBX2O0GDdplN0IWaa7cfZxMAJ3hc4a4JEc/French_Female.mp3"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

text-to-speech, tts, audio, voice-synthesis, voice-cloning, multilingual, resemble-ai, open-source

## Documentation

https://replicate.com/resemble-ai/chatterbox-multilingual