# Chatterbox TTS

> Turn text into expressive speech and clone any voice from a short reference recording, with fine control over emotional intensity.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech`
- **Model ID**: `resemble-ai/chatterbox/text-to-speech`
- **Category**: sound
- **Kind**: inference
- **Tags**: resemble-ai, chatterbox, text-to-speech, tts, voice-cloning, 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` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). 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/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/resemble-ai/chatterbox/text-to-speech/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

- **`cfg`** (`number`, _optional_):
  Classifier-free guidance weight. Higher values track the reference voice and prompt more closely; lower values give the model more freedom.
  - Default: `0.5`
  - Range: `0.1` to `1`

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducibility. Set a fixed integer to repeat a generation; 0 or unset uses a random seed.

- **`text`** (`string`, _required_):
  The text to synthesize into speech. Up to 5000 characters. Supports inline emotive tags such as <laugh>, <sigh>, <gasp>, and <cough> to shape delivery.

- **`audio_url`** (`string | null`, _optional_):
  Optional reference recording whose voice and style are cloned. Provide a clean, single-speaker clip to clone that voice; leave it unset to use the built-in default voice.

- **`temperature`** (`number`, _optional_):
  Sampling temperature. Lower is steadier and more predictable; higher adds variation to prosody and delivery.
  - Default: `0.7`
  - Range: `0.05` to `2`

- **`exaggeration`** (`number`, _optional_):
  Emotion and intensity exaggeration. Higher values produce more dramatic, expressive delivery; lower values are calmer and more measured.
  - Default: `0.25`
  - Range: `0` to `1`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "cfg": 0.5,
  "text": "Pack light, move fast, and never book the same hotel twice. That is how you find the stories worth telling.",
  "audio_url": "https://media.modelrunner.ai/LgBvbcVQn74cCGHEvWfzT.mp3",
  "temperature": 0.7,
  "exaggeration": 0.25
}
```

**Output**

```json
"https://media.modelrunner.ai/MdFN9UEpl0kXMbdD4AIKX.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 \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "cfg": 0.5,
  "text": "Pack light, move fast, and never book the same hotel twice. That is how you find the stories worth telling.",
  "audio_url": "https://media.modelrunner.ai/LgBvbcVQn74cCGHEvWfzT.mp3",
  "temperature": 0.7,
  "exaggeration": 0.25
}')

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", {
  input: {
  "cfg": 0.5,
  "text": "Pack light, move fast, and never book the same hotel twice. That is how you find the stories worth telling.",
  "audio_url": "https://media.modelrunner.ai/LgBvbcVQn74cCGHEvWfzT.mp3",
  "temperature": 0.7,
  "exaggeration": 0.25
}
});

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",
        arguments={
  "cfg": 0.5,
  "text": "Pack light, move fast, and never book the same hotel twice. That is how you find the stories worth telling.",
  "audio_url": "https://media.modelrunner.ai/LgBvbcVQn74cCGHEvWfzT.mp3",
  "temperature": 0.7,
  "exaggeration": 0.25
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

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