Name: Chatterbox Multilingual API: TTS and Voice Cloning
Brand: magicapi
SKU: api-magicapi-multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual
Availability: InStock
Author: API Market

Shashank Agarwal

# 🗣️ Multilingual Text-to-Speech and Voice Cloning API (Resemble AI Chatterbox Multilingual)

## Overview
Chatterbox Multilingual is a text-to-speech model from Resemble AI. Its developer describes it as generating expressive, natural speech in 23 languages, with instant voice cloning from short audio, emotion control and cross-language voice transfer.

Send up to 300 characters of `text` and a `language`. Add a short `reference_audio` clip to speak in that voice; without it, the default voice for the language is used. Each request returns the URL of one audio file.

## Features
- **23 languages**: Arabic (`ar`), Danish (`da`), German (`de`), Greek (`el`), English (`en`, default), Spanish (`es`), Finnish (`fi`), French (`fr`), Hebrew (`he`), Hindi (`hi`), Italian (`it`), Japanese (`ja`), Korean (`ko`), Malay (`ms`), Dutch (`nl`), Norwegian (`no`), Polish (`pl`), Portuguese (`pt`), Russian (`ru`), Swedish (`sv`), Swahili (`sw`), Turkish (`tr`) and Chinese (`zh`).
- **Voice cloning**: send a short `reference_audio` clip and the speech uses that voice.
- **Expressiveness**: `exaggeration` runs from 0.25 to 2.0 (neutral 0.5); the developer notes that extreme values may be unstable.
- **Variation and pace**: `temperature` (0.05 to 5.0, default 0.8) controls randomness, `cfg_weight` (0.2 to 1.0, default 0.5) controls guidance and pace.
- **Seed**: set `seed` to reproduce a result; `0` (default) picks a random seed.

## Use Cases
1. **Voice-overs in many languages**: narrate product videos, tutorials and announcements in the language of each market.
2. **Branded voices**: clone a voice you have the rights to from a short clip and reuse it across languages.
3. **Apps and games**: generate short spoken lines (up to 300 characters per request) on demand.
4. **Accessibility**: read short texts aloud in the reader's language.

## Visual Examples
### Example Input
Text (French): "Bienvenue sur api.market. Cette voix a été générée à partir d'un court extrait audio de référence. Elle peut lire des annonces, des tutoriels ou des messages d'accueil dans de nombreuses langues, avec un ton naturel et expressif."

[Listen to the reference audio](https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-input-api-market.mp3)

Settings: `language` `fr`, `exaggeration` `0.5`, `temperature` `0.8`, `cfg_weight` `0.5`, `seed` `0`.

### Example Output
The French text spoken in the voice of the reference audio.

[Listen to the example output](https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-output-1wvc5yhb-api-market.mp3)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | Yes | none |  | Text to synthesize into speech (maximum 300 characters) |
| `language` | string | No | `en` | `ar`, `da`, `de`, `el`, `en`, `es`, `fi`, `fr`, `he`, `hi`, `it`, `ja`, `ko`, `ms`, `nl`, `no`, `pl`, `pt`, `ru`, `sv`, `sw`, `tr`, `zh` | Language for synthesis |
| `reference_audio` | string (URL) | No | none |  | Reference audio file URL for voice cloning (optional). If not provided, the default voice for the selected language is used |
| `exaggeration` | number | No | `0.5` | 0.25 to 2 | Controls speech expressiveness (0.25 to 2.0, neutral 0.5; extreme values may be unstable) |
| `temperature` | number | No | `0.8` | 0.05 to 5 | Controls randomness in generation (0.05 to 5.0; higher is more varied) |
| `cfg_weight` | number | No | `0.5` | 0.2 to 1 | CFG/pace weight controlling generation guidance (0.2 to 1.0). Use 0.5 for balanced results |
| `seed` | integer | No | `0` |  | Random seed for reproducible results (0 for random generation) |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0089 per API unit.
- **1 API unit = 1 request with up to 8 seconds of processing.** A request that takes longer uses one unit per started block of 8 seconds (for example, 10 seconds of processing uses 2 units, $0.0178).
- Longer texts take longer to generate and can use more units.
- **Example cost**: the example request (229 characters of French with a reference voice) took 5.3 seconds of processing, which is 1 unit = **$0.0089**.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "9cfba4c265e685f840612be835424f8c33bdee685d7466ece7684b0d9d4c0b1c",
    "input": {
      "seed": 0,
      "text": "Bienvenue sur api.market. Cette voix a été générée à partir d'\''un court extrait audio de référence. Elle peut lire des annonces, des tutoriels ou des messages d'\''accueil dans de nombreuses langues, avec un ton naturel et expressif.",
      "language": "fr",
      "cfg_weight": 0.5,
      "temperature": 0.8,
      "exaggeration": 0.5,
      "reference_audio": "https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-input-api-market.mp3"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "1wvc5yhba5rmr0d1d218ywf86r",
  "version": "9cfba4c265e685f840612be835424f8c33bdee685d7466ece7684b0d9d4c0b1c",
  "status": "starting",
  "created_at": "2026-10-23T11:25:23.827Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "1wvc5yhba5rmr0d1d218ywf86r",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-output-1wvc5yhb-api-market.mp3",
  "error": null,
  "created_at": "2026-10-23T11:25:23.827Z",
  "started_at": "2026-10-23T11:25:24.327Z",
  "completed_at": "2026-10-23T11:25:29.104Z"
}
```

`output` is a single URL string pointing to the generated audio file.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `text`, a `language` that is not in the list, or an `exaggeration` outside 0.25 to 2.0.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "9cfba4c265e685f840612be835424f8c33bdee685d7466ece7684b0d9d4c0b1c", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "seed": 0,
  "text": "Bienvenue sur api.market. Cette voix a été générée à partir d'un court extrait audio de référence. Elle peut lire des annonces, des tutoriels ou des messages d'accueil dans de nombreuses langues, avec un ton naturel et expressif.",
  "language": "fr",
  "cfg_weight": 0.5,
  "temperature": 0.8,
  "exaggeration": 0.5,
  "reference_audio": "https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-input-api-market.mp3"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/multilingual-voice-cloning-emotion-control-resemble-ai-chatterbox-multilingual"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "9cfba4c265e685f840612be835424f8c33bdee685d7466ece7684b0d9d4c0b1c", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


output = create_and_wait_for_prediction({
    "seed": 0,
    "text": "Bienvenue sur api.market. Cette voix a été générée à partir d'un court extrait audio de référence. Elle peut lire des annonces, des tutoriels ou des messages d'accueil dans de nombreuses langues, avec un ton naturel et expressif.",
    "language": "fr",
    "cfg_weight": 0.5,
    "temperature": 0.8,
    "exaggeration": 0.5,
    "reference_audio": "https://blog.api.market/wp-content/uploads/2026/10/chatterbox-multilingual-input-api-market.mp3"
})
print(output)
```

## FAQ
- **How long can the text be?**
  - Up to 300 characters per request. Split longer texts into several requests.
- **Do I need a reference voice?**
  - No. Without `reference_audio`, the default voice for the selected `language` is used.
- **Can a voice speak a language it was not recorded in?**
  - Yes. Send a `reference_audio` clip in one language and set `language` to another; the developer describes this as cross-language voice transfer.
- **How do I make the speech more expressive?**
  - Raise `exaggeration` above the neutral 0.5 (up to 2.0). Very high values may be unstable.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Generate expressive speech in 23 languages with Resemble AI's Chatterbox Multilingual, with voice cloning from a short clip and emotion control.