# Chatterbox Multilingual TTS

> Turn text into natural speech across 23 languages with a language selector and emotion-intensity control.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual`
- **Model ID**: `resemble-ai/chatterbox/text-to-speech/multilingual`
- **Category**: sound
- **Kind**: inference
- **Tags**: resemble-ai, chatterbox, text-to-speech, tts, multilingual, voice, audio, speech

## Pricing

- **Price**: $0.000375 per output second

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual` with a JSON body. The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducible results. Set to 0 for random generation, or provide a specific number for consistent outputs.

- **`text`** (`string`, _required_):
  The text to synthesize into speech (maximum 300 characters). Supports 23 languages including English, French, German, Spanish, Italian, Portuguese, Hindi, Arabic, Chinese, Japanese, Korean, and more.

- **`voice`** (`VoiceEnum`, _optional_):
  Language for speech synthesis. Select the language that matches your text so pronunciation and prosody are correct.
  - Default: `"english"`
  - Options: `"english"`, `"arabic"`, `"danish"`, `"german"`, `"greek"`, `"spanish"`, `"finnish"`, `"french"`, `"hebrew"`, `"hindi"`, `"italian"`, `"japanese"`, `"korean"`, `"malay"`, `"dutch"`, `"norwegian"`, `"polish"`, `"portuguese"`, `"russian"`, `"swedish"`, `"swahili"`, `"turkish"`, `"chinese"`

- **`cfg_scale`** (`number`, _optional_):
  Configuration/pace weight controlling generation guidance (0.0-1.0). Use 0.0 for language transfer to mitigate accent inheritance.
  - Default: `0.5`
  - Range: `0` to `1`

- **`temperature`** (`number`, _optional_):
  Controls randomness and variation in generation (0.05-5.0). Higher values create more varied speech patterns.
  - Default: `0.8`
  - Range: `0.05` to `5`

- **`exaggeration`** (`number`, _optional_):
  Controls speech expressiveness and emotional intensity (0.25-2.0). 0.5 is neutral, higher values increase expressiveness. Extreme values may be unstable.
  - Default: `0.5`
  - Range: `0.25` to `2`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "text": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "voice": "spanish",
  "prompt": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "cfg_scale": 0.5,
  "temperature": 0.8,
  "exaggeration": 0.5
}
```

**Output**

```json
"https://media.modelrunner.ai/pShXgY36rCrVf0796FeaF.wav"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/multilingual \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "text": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "voice": "spanish",
  "prompt": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "cfg_scale": 0.5,
  "temperature": 0.8,
  "exaggeration": 0.5
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("resemble-ai/chatterbox/text-to-speech/multilingual", {
  input: {
  "text": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "voice": "spanish",
  "prompt": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "cfg_scale": 0.5,
  "temperature": 0.8,
  "exaggeration": 0.5
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "resemble-ai/chatterbox/text-to-speech/multilingual",
        arguments={
  "text": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "voice": "spanish",
  "prompt": "Hola y bienvenido. Genera voces naturales y expresivas en veintitrés idiomas, listas para tus vídeos y aplicaciones.",
  "cfg_scale": 0.5,
  "temperature": 0.8,
  "exaggeration": 0.5
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/resemble-ai/chatterbox/text-to-speech/multilingual)
- [OpenAPI Schema](https://modelrunner.ai/models/resemble-ai/chatterbox/text-to-speech/multilingual/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/resemble-ai/chatterbox/text-to-speech/multilingual/llms.txt)