# Tada 3B Text to Speech — API Reference

Model ID: `model_tada-3b-text-to-speech`

---

## Authentication

Scenario API uses HTTP Basic Auth. Encode your credentials in Base64 and pass them as the `Authorization` header.

```
Authorization: Basic base64("<API_KEY>:<API_SECRET>")
```

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=project_api_keys) under API Keys.
- In shell: `$(echo -n '<API_KEY>:<API_SECRET>' | base64)`
- In JavaScript: `btoa("<API_KEY>:<API_SECRET>")`
- In Python: `base64.b64encode(f"{api_key}:{api_secret}".encode()).decode()`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_tada-3b-text-to-speech`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Text to synthesize with the reference voice. |
| `transcript` | string | - | `` | Transcript of the reference audio. Required for non-English references. |
| `language` | string | - | `en` | Language used for text alignment. |
| `numInferenceSteps` | number | - | `20` | Number of ODE solver steps for acoustic generation. |
| `speedUpFactor` | number | - | `1` | Values > 1 speed up and values < 1 slow down speech. |
| `temperature` | number | - | `0.6` | Sampling temperature for text token generation. |
| `topP` | number | - | `0.9` | Top-p nucleus sampling value. |
| `repetitionPenalty` | number | - | `1.1` | Penalty applied to repeated tokens. |
| `acousticCfgScale` | number | - | `1.6` | Classifier-free guidance scale for acoustic generation. |
| `noiseTemperature` | number | - | `0.9` | Temperature for diffusion noise during flow matching. |
| `numExtraSteps` | number | - | `0` | Additional autoregressive steps for continuation. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_tada-3b-text-to-speech" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "transcript": "",
  "language": "en",
  "numInferenceSteps": 20,
  "speedUpFactor": 1,
  "temperature": 0.6,
  "topP": 0.9,
  "repetitionPenalty": 1.1,
  "acousticCfgScale": 1.6,
  "noiseTemperature": 0.9,
  "numExtraSteps": 0
}
EOF
```

**Python**

```python
import requests
import base64

api_key = "<API_KEY>"
api_secret = "<API_SECRET>"
token = base64.b64encode(f"{api_key}:{api_secret}".encode()).decode()

url = "https://api.cloud.scenario.com/v1/generate/custom/model_tada-3b-text-to-speech"
headers = {
    "Authorization": f"Basic {token}",
    "Content-Type": "application/json"
}
payload = {
    "prompt": "A fantasy landscape",
    "transcript": "",
    "language": "en",
    "numInferenceSteps": 20,
    "speedUpFactor": 1,
    "temperature": 0.6,
    "topP": 0.9,
    "repetitionPenalty": 1.1,
    "acousticCfgScale": 1.6,
    "noiseTemperature": 0.9,
    "numExtraSteps": 0
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())
```

**JavaScript**

```javascript
const token = btoa("<API_KEY>:<API_SECRET>");

const body = {
  "prompt": "A fantasy landscape",
  "transcript": "",
  "language": "en",
  "numInferenceSteps": 20,
  "speedUpFactor": 1,
  "temperature": 0.6,
  "topP": 0.9,
  "repetitionPenalty": 1.1,
  "acousticCfgScale": 1.6,
  "noiseTemperature": 0.9,
  "numExtraSteps": 0
};

const response = await fetch(
  "https://api.cloud.scenario.com/v1/generate/custom/model_tada-3b-text-to-speech",
  {
    method: "POST",
    headers: {
      "Authorization": `Basic ${token}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify(body),
  }
);

const data = await response.json();
console.log(data);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job status endpoint until the job completes.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

**Headers:**
```
Authorization: Basic base64("<API_KEY>:<API_SECRET>")
```

Poll until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Example response:**
```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/docs/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*