# Drama-3 Text to Audio

> AI model for generating voice cloning content

## Overview

- **Model ID**: `drama-3`
- **Category**: voice cloning
- **Provider**: modelslab
- **Source Type**: Open Source Model
- **Status**: model_ready
- **Screenshot**: `https://assets.modelslab.ai/generations/f42fce40-23c2-4b88-949f-16d7668241c0.png`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v6/voice/text_to_audio`
- **Method**: POST

### Parameters

- **`init_audio`** (required): init_audio
  - Type: file (audio/mp3,audio/wav,audio/mp4)
  - Example: Enter Audio URL

- **`prompt`** (required): Prompt
  - Type: textarea

- **`language`** (required): language
  - Type: select (options: arabic, assamese, bengali, brazilian, chinese, czech, danish, dutch, english, finnish, french, german, greek, gujarati, hebrew, hindi, hungarian, indonesian, italian, japanese, kannada, korean, maithili, malay, malayalam, marathi,  chinese, nepali, odia, persian, polish, punjabi, russian, sindhi, sinhala, slovak, spanish, swahili, swedish, tamil, telugu, thai, turkish, ukrainian, urdu, vietnamese, welsh)
  - Example: language

- **`temperature`** (optional): Drama 3 only. Sampling temperature; higher values give more varied delivery.
  - Type: number

- **`top_p`** (optional): Drama 3 only. Nucleus sampling threshold.
  - Type: number

- **`top_k`** (optional): Drama 3 only. Number of most likely tokens sampled from at each step.
  - Type: number (range: 1-100)

- **`max_new_tokens`** (optional): Drama 3 only. Maximum number of audio tokens to generate; caps the output length.
  - Type: number (range: 1-2028)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/voice/text_to_audio \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "drama-3",
    "init_audio": "https://assets.modelslab.ai/generations/cfdf9e1b-a7d9-45ef-b2a2-da9cde7aa732.mp3",
    "prompt": "Hello! This is a test of the Drama Three audio model.Today, we're going to explore how clearly and naturally this model can speak. Please pay attention to the pronunciation of each word, the rhythm of the sentences, the pauses between phrases, and the overall quality of the voice.First, let's try a calm and friendly tone. Hello, everyone! It's a beautiful day, and I'm delighted to be here with you.Next, let's introduce a little excitement. Wow! This is incredible! I can't believe how amazing this experience is. Let's see what happens next!",
    "language": "english",
    "temperature": "1.0",
    "top_p": "0.9",
    "top_k": "30",
    "max_new_tokens": "1024"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/voice/text_to_audio",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "drama-3",
        "init_audio": "https://assets.modelslab.ai/generations/cfdf9e1b-a7d9-45ef-b2a2-da9cde7aa732.mp3",
        "prompt": "Hello! This is a test of the Drama Three audio model.Today, we're going to explore how clearly and naturally this model can speak. Please pay attention to the pronunciation of each word, the rhythm of the sentences, the pauses between phrases, and the overall quality of the voice.First, let's try a calm and friendly tone. Hello, everyone! It's a beautiful day, and I'm delighted to be here with you.Next, let's introduce a little excitement. Wow! This is incredible! I can't believe how amazing this experience is. Let's see what happens next!",
        "language": "english",
        "temperature": "1.0",
        "top_p": "0.9",
        "top_k": "30",
        "max_new_tokens": "1024"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/voice/text_to_audio", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "drama-3",
    "init_audio": "https://assets.modelslab.ai/generations/cfdf9e1b-a7d9-45ef-b2a2-da9cde7aa732.mp3",
    "prompt": "Hello! This is a test of the Drama Three audio model.Today, we're going to explore how clearly and naturally this model can speak. Please pay attention to the pronunciation of each word, the rhythm of the sentences, the pauses between phrases, and the overall quality of the voice.First, let's try a calm and friendly tone. Hello, everyone! It's a beautiful day, and I'm delighted to be here with you.Next, let's introduce a little excitement. Wow! This is incredible! I can't believe how amazing this experience is. Let's see what happens next!",
    "language": "english",
    "temperature": "1.0",
    "top_p": "0.9",
    "top_k": "30",
    "max_new_tokens": "1024"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Integration Options

### CLI

Install: `curl -fsSL https://modelslab.sh/install.sh | sh` or `brew install modelslab/tap/modelslab`

```bash
modelslab auth login                                    # Authenticate
modelslab models search "drama-3"                       # Find this model
modelslab models detail --id drama-3                    # Get model details
modelslab generate image --prompt "..." --model drama-3  # Generate with model
modelslab config set generation.default_model drama-3   # Set as default
```

- Website: https://modelslab.sh
- GitHub: https://github.com/ModelsLab/modelslab-cli

### MCP Servers (Model Context Protocol)

For Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible agent.

- Generation: `https://modelslab.com/mcp/v7` (API key auth, 23 tools)
- Agent Control Plane: `https://modelslab.com/mcp/agents` (Bearer token auth, 10 tools)

Claude Code config (`~/.claude/settings.json`):

```json
{
  "mcpServers": {
    "modelslab-v7": {
      "url": "https://modelslab.com/mcp/v7",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

- Documentation: https://docs.modelslab.com/mcp-web-api/overview

### Agent Skills

Install skill files directly into AI coding agents:

```bash
npx skills add modelslab/skills --all                          # All skills
npx skills add modelslab/skills --skill image-generation       # Specific skill
npx skills add modelslab/skills --all -a claude-code -a cursor # Target agents
```

- GitHub: https://github.com/ModelsLab/skills
- Documentation: https://docs.modelslab.com/agent-skills

### SDKs

- Python: `pip install modelslab`
- TypeScript: `npm install modelslab`
- PHP: `composer require modelslab/modelslab`
- Go: `go get github.com/modelslab/modelslab-go`
- Dart: `dart pub add modelslab`

## Links

- [Model Playground](https://modelslab.com/models/modelslab/drama-3)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)