# Chatterbox Turbo

> Resemble AI's fastest open-source TTS. 20 pre-made voices, paralinguistic tags like [sigh] and [chuckle], and optional instant voice cloning from 5s+ reference audio. Max 500 characters per request.

- **Provider**: replicate
- **Model ID**: resemble-ai/chatterbox-turbo
- **Category**: tts_voice
- **Credits**: 59 per request
- **Pricing Type**: token_based

## 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

- `top_k` (integer, optional): Top-k sampling. Limits vocabulary to top k tokens at each step. (Default: `1000`; Range: min: 1, max: 2000)
- `reference_audio` (string, optional): Reference audio file for voice cloning (optional). Must be longer than 5 seconds. If provided, overrides the voice selection.
- `text` (string, **required**): Text to synthesize into speech (maximum 500 characters).

Supported paralinguistic tags you can include in your text:
[clear throat], [sigh], [sush], [cough], [groan], [sniff], [gasp], [chuckle], [laugh]

Example: "Oh, that's hilarious! [chuckle] Let me tell you more."
- `repetition_penalty` (number, optional): Penalizes token repetition. Higher values reduce repetition. (Default: `1.2`; Range: min: 1, max: 2)
- `top_p` (number, optional): Nucleus sampling threshold. Lower values make output more focused. (Default: `0.95`; Range: min: 0.5, max: 1)
- `temperature` (number, optional): Controls randomness in generation. Higher values produce more varied speech. (Default: `0.8`; Range: min: 0.05, max: 2)
- `voice` (string, optional): Pre-made voice to use for synthesis. Ignored if reference_audio is provided. (Default: `Andy`; Options: `Aaron`, `Abigail`, `Anaya`, `Andy`, `Archer`, `Brian`, `Chloe`, `Dylan`, `Emmanuel`, `Ethan`, `Evelyn`, `Gavin`, `Gordon`, `Ivan`, `Laura`, `Lucy`, `Madison`, `Marisol`, `Meera`, `Walter`)
- `seed` (integer, optional): Random seed for reproducible results. Leave blank for random generation.

## Example Request

```json
{
  "model": "resemble-ai/chatterbox-turbo",
  "input": {
    "top_p": 0.95,
    "voice": "Abigail",
    "temperature": 0.8,
    "text": "Oh, that's hilarious! [chuckle] Um anyway, we do have a new model in store. It's the SkyNet T-800 series and it's got basically everything. Including AI integration with ChatGPT and all that jazz. Would you like me to get some prices for you?",
    "repetition_penalty": 1.2,
    "reference_audio": "https://replicate.delivery/pbxt/OEt67TSAP4l1Aq36bC3DSaRR1oQ5VT5prVkVh0yioOWJBTiO/voice.wav"
  }
}
```

## 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, resemble-ai, open-source, low-latency

## Documentation

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


## Token Pricing

- Input: 0.058125 credits/token
- Output: 0.058125 credits/token