### Generate video

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Example usage for generating a video. Define completion rules before starting.

```python
from minimax import Minimax

minimax = Minimax(api_key="YOUR_API_KEY")

# Generate a video
minimax.generate_video(
    prompt="A futuristic cityscape at sunset",
    output_path="output.mp4",
    completion_rules=["rule1", "rule2"]
)
```

--------------------------------

### MinimaxAPIClient Initialization and Usage

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Demonstrates how to initialize the MinimaxAPIClient and make common API requests like POST for text-to-speech and GET for querying status. It also shows an example of file upload for voice cloning.

```APIDOC
## MinimaxAPIClient

The underlying API client handles authentication and requests to MiniMax endpoints.

### Description
This section details the initialization and usage of the `MinimaxAPIClient` for interacting with MiniMax AI services.

### Method
Initialization and various HTTP methods (POST, GET).

### Endpoint
`/v1/t2a_v2`, `/v1/query/video_generation`, `/v1/files/upload`

### Parameters
#### Path Parameters
None for initialization. Specific endpoints have their own parameters.

#### Query Parameters
- **task_id** (string) - Required - The ID of the video generation task to query.

#### Request Body
##### POST /v1/t2a_v2
- **model** (string) - Required - The text-to-speech model to use (e.g., "speech-2.6-hd").
- **text** (string) - Required - The text to convert to speech.
- **voice_setting** (object) - Required - Settings for the voice.
  - **voice_id** (string) - Required - The ID of the voice to use (e.g., "female-shaonv").
  - **speed** (float) - Optional - The speaking speed (default: 1.0).
  - **vol** (float) - Optional - The volume (default: 1.0).
  - **pitch** (integer) - Optional - The pitch (default: 0).
  - **emotion** (string) - Optional - The emotion of the voice (e.g., "happy").
- **audio_setting** (object) - Required - Settings for the audio output.
  - **sample_rate** (integer) - Optional - The sample rate of the audio (default: 32000).
  - **bitrate** (integer) - Optional - The bitrate of the audio (default: 128000).
  - **format** (string) - Optional - The audio format (e.g., "mp3").
  - **channel** (integer) - Optional - The number of audio channels (default: 1).

##### POST /v1/files/upload
- **file** (file) - Required - The audio file to upload for voice cloning.
- **purpose** (string) - Required - The purpose of the file upload (e.g., "voice_clone").

### Request Example
```python
from minimax_mcp.client import MinimaxAPIClient

client = MinimaxAPIClient(
    api_key="your-api-key",
    api_host="https://api.minimax.io"
)

# Text-to-speech example
response_tts = client.post("/v1/t2a_v2", json={
    "model": "speech-2.6-hd",
    "text": "Hello world",
    "voice_setting": {
        "voice_id": "female-shaonv",
        "speed": 1.0,
        "vol": 1.0,
        "pitch": 0,
        "emotion": "happy"
    },
    "audio_setting": {
        "sample_rate": 32000,
        "bitrate": 128000,
        "format": "mp3",
        "channel": 1
    }
})

# Query video status example
status = client.get("/v1/query/video_generation?task_id=abc123")

# File upload for voice cloning example
with open("sample.mp3", "rb") as f:
    response_upload = client.post(
        "/v1/files/upload",
        files={"file": f},
        data={"purpose": "voice_clone"}
    )
```

### Response
#### Success Response (200)
- **response_tts** (object) - The response from the text-to-speech API.
- **status** (object) - The status of the video generation task.
- **response_upload** (object) - The response from the file upload API.

#### Response Example
```json
{
  "message": "Success",
  "data": { ... }
}
```
```

--------------------------------

### Generate images

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Example usage for generating images. Provide a prompt and specify the output path.

```python
from minimax import Minimax

minimax = Minimax(api_key="YOUR_API_KEY")

# Generate images
minimax.generate_images(
    prompt="A serene forest landscape",
    output_path="output.png"
)
```

--------------------------------

### Clone a voice

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Example usage for cloning a voice. Ensure you have the necessary audio data.

```python
from minimax import Minimax

minimax = Minimax(api_key="YOUR_API_KEY")

# Clone a voice
minimax.clone_voice(
    name="My Voice",
    audio_file="path/to/your/audio.wav"
)
```

--------------------------------

### Clone Voice from Audio

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Tool call examples for cloning a voice using a local file or a URL. Requires a source file and a target voice ID.

```python
# Clone from local file
{
    "voice_id": "my_custom_voice",
    "file": "/path/to/voice_sample.mp3",
    "text": "This is a demo of my cloned voice.",
    "is_url": false,
    "output_directory": "~/Desktop/cloned"
}

# Clone from URL
{
    "voice_id": "narrator_voice",
    "file": "https://example.com/sample_audio.mp3",
    "text": "Testing the cloned narrator voice.",
    "is_url": true,
    "output_directory": "~/Desktop/cloned"
}
```

--------------------------------

### List Available Voices

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Tool call examples for retrieving system or custom cloned voices. Allows filtering by voice type.

```python
# List all voices
{
    "voice_type": "all"
}

# List system voices
{
    "voice_type": "system"
}

# List cloned voices
{
    "voice_type": "voice_cloning"
}
```

--------------------------------

### Initialize and Use MinimaxAPIClient in Python

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Demonstrates how to initialize the MinimaxAPIClient with API credentials and make various requests to MiniMax endpoints. This includes POST requests for text-to-speech and file uploads, as well as GET requests for querying video generation status. It requires the 'minimax-mcp' library.

```python
from minimax_mcp.client import MinimaxAPIClient

# Initialize client
client = MinimaxAPIClient(
    api_key="your-api-key",
    api_host="https://api.minimax.io"
)

# Make POST request (e.g., text-to-speech)
response = client.post("/v1/t2a_v2", json={
    "model": "speech-2.6-hd",
    "text": "Hello world",
    "voice_setting": {
        "voice_id": "female-shaonv",
        "speed": 1.0,
        "vol": 1.0,
        "pitch": 0,
        "emotion": "happy"
    },
    "audio_setting": {
        "sample_rate": 32000,
        "bitrate": 128000,
        "format": "mp3",
        "channel": 1
    }
})

# Make GET request (e.g., query video status)
status = client.get("/v1/query/video_generation?task_id=abc123")

# File upload for voice cloning
with open("sample.mp3", "rb") as f:
    response = client.post(
        "/v1/files/upload",
        files={"file": f},
        data={"purpose": "voice_clone"}
    )
```

--------------------------------

### Convert Text to Audio

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Tool call examples for text-to-speech synthesis. Supports basic and advanced parameters like voice ID, speed, pitch, emotion, and output formatting.

```python
# Basic usage
{
    "text": "Hello, welcome to MiniMax text-to-speech service!",
    "output_directory": "~/Desktop/audio"
}

# Advanced usage
{
    "text": "Breaking news: Scientists have made a groundbreaking discovery.",
    "voice_id": "male-qn-qingse",
    "model": "speech-2.6-hd",
    "speed": 1.2,
    "vol": 1.5,
    "pitch": 2,
    "emotion": "neutral",
    "sample_rate": 44100,
    "bitrate": 256000,
    "channel": 2,
    "format": "mp3",
    "language_boost": "English",
    "output_directory": "~/Desktop/news"
}
```

--------------------------------

### Broadcast news segment

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Example usage for broadcasting a segment of the evening news.

```python
from minimax import Minimax

minimax = Minimax(api_key="YOUR_API_KEY")

# Broadcast a segment of the evening news
minimax.broadcast_news(
    title="Evening News",
    segment_url="https://example.com/news_segment.mp4",
    description="A summary of today's top stories."
)
```

--------------------------------

### Play Audio Files

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Plays audio files from local paths or remote URLs. Requires ffmpeg installed on the host system.

```json
{
    "input_file_path": "https://cdn.minimax.io/audio/sample.mp3",
    "is_url": true
}
```

--------------------------------

### Design Custom Voice

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Tool call examples for generating a new voice based on a descriptive text prompt. Supports optional manual voice ID assignment.

```python
# Create voice with ID
{
    "prompt": "A warm, friendly female voice in her 30s with a slight British accent, suitable for audiobook narration",
    "preview_text": "Welcome to this exciting adventure story. Let me take you on a journey through mysterious lands.",
    "voice_id": "audiobook_narrator",
    "output_directory": "~/Desktop/voices"
}

# Create voice with auto-generated ID
{
    "prompt": "Young energetic male voice, enthusiastic and upbeat, perfect for sports commentary",
    "preview_text": "And the crowd goes wild! What an incredible play!"
}
```

--------------------------------

### Configure Environment Variables

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Sets up the MCP server environment, including API credentials, host endpoints, and default file output directories.

```bash
MINIMAX_API_KEY=your-api-key-here
MINIMAX_API_HOST=https://api.minimax.io
MINIMAX_MCP_BASE_PATH=~/Desktop
```

--------------------------------

### Configure Claude Desktop for MiniMax MCP

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Add this configuration to your claude_desktop_config.json to enable the MiniMax MCP server. Ensure your MINIMAX_API_KEY and MINIMAX_API_HOST are correctly set for your region.

```json
{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_MCP_BASE_PATH": "local-output-dir-path, such as /User/xxx/Desktop",
        "MINIMAX_API_HOST": "api host, https://api.minimax.io | https://api.minimaxi.com",
        "MINIMAX_API_RESOURCE_MODE": "optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format"
      }
    }
  }
}
```

--------------------------------

### POST /query_video_generation

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Checks the status of an asynchronous video generation task and retrieves the final output.

```APIDOC
## POST /query_video_generation

### Description
Polls the status of a previously submitted asynchronous video generation task.

### Method
POST

### Parameters
#### Request Body
- **task_id** (string) - Required - The ID returned from the initial generation request
- **output_directory** (string) - Required - Path to save the completed file

### Request Example
{
  "task_id": "task_abc123",
  "output_directory": "~/Desktop/videos"
}

### Response
#### Success Response (200)
- **status** (string) - Current status (processing, completed, or failed)

#### Response Example
{
  "message": "Success. Video saved as: ~/Desktop/videos/video_task_abc123.mp4"
}
```

--------------------------------

### Find uvx executable path

Source: https://github.com/minimax-ai/minimax-mcp/blob/main/README.md

Use this command to find the absolute path of the uvx executable if it's not found. Update your configuration with the obtained path.

```sh
which uvx
```

--------------------------------

### POST voice_clone

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Creates a new voice profile from an existing audio sample.

```APIDOC
## POST voice_clone

### Description
Clone a voice from an audio sample file. The cloned voice can be used in subsequent text-to-speech calls.

### Method
POST

### Endpoint
voice_clone

### Parameters
#### Request Body
- **voice_id** (string) - Required - Unique identifier for the new voice.
- **file** (string) - Required - Path or URL to the audio sample.
- **is_url** (boolean) - Required - Whether the file input is a URL.
- **output_directory** (string) - Required - Directory to store the demo output.

### Request Example
{
  "voice_id": "my_custom_voice",
  "file": "/path/to/sample.mp3",
  "is_url": false
}

### Response
#### Success Response (200)
- **status** (string) - Success confirmation and file path.
```

--------------------------------

### POST /generate_video

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Generates video content from text prompts or image-to-video inputs with support for director-style camera controls and asynchronous processing.

```APIDOC
## POST /generate_video

### Description
Generates a video based on a prompt. Supports T2V (text-to-video), I2V (image-to-video), and Director models.

### Method
POST

### Parameters
#### Request Body
- **model** (string) - Required - The model identifier (e.g., T2V-01, I2V-01, MiniMax-Hailuo-02)
- **prompt** (string) - Required - The descriptive text for video generation
- **output_directory** (string) - Required - Local path to save the generated file
- **first_frame_image** (string) - Optional - Path to the starting frame for I2V models
- **duration** (integer) - Optional - Duration in seconds
- **resolution** (string) - Optional - Output resolution (e.g., 1080P)
- **async_mode** (boolean) - Optional - If true, returns a task ID for background processing

### Request Example
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "A futuristic cityscape",
  "output_directory": "~/Desktop/videos"
}

### Response
#### Success Response (200)
- **message** (string) - Confirmation message with file path or task ID

#### Response Example
{
  "message": "Success. Video saved as: ~/Desktop/videos/video_task123.mp4"
}
```

--------------------------------

### POST /text_to_image

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Generates images from text prompts with support for batching and aspect ratio configuration.

```APIDOC
## POST /text_to_image

### Description
Creates high-quality images based on provided prompts.

### Method
POST

### Parameters
#### Request Body
- **prompt** (string) - Required - Description of the image
- **aspect_ratio** (string) - Optional - Desired ratio (e.g., 16:9, 3:4)
- **n** (integer) - Optional - Number of images to generate
- **output_directory** (string) - Required - Path to save images

### Request Example
{
  "prompt": "Cyberpunk street scene",
  "aspect_ratio": "16:9",
  "n": 1,
  "output_directory": "~/Desktop/images"
}

### Response
#### Success Response (200)
- **files** (array) - List of paths to generated images
```

--------------------------------

### POST text_to_audio

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Converts input text into high-quality audio using specified voice models and parameters.

```APIDOC
## POST text_to_audio

### Description
Convert text to audio with customizable voice, speed, pitch, emotion, and audio format settings.

### Method
POST

### Endpoint
text_to_audio

### Parameters
#### Request Body
- **text** (string) - Required - The text content to synthesize.
- **output_directory** (string) - Required - Local path to save the generated file.
- **voice_id** (string) - Optional - The ID of the voice to use.
- **model** (string) - Optional - The speech model version.
- **speed** (float) - Optional - Playback speed multiplier.
- **vol** (float) - Optional - Volume level.
- **pitch** (float) - Optional - Pitch adjustment.
- **format** (string) - Optional - Audio output format (e.g., mp3, wav).

### Request Example
{
  "text": "Hello, welcome to MiniMax!",
  "voice_id": "male-qn-qingse",
  "output_directory": "~/Desktop/audio"
}

### Response
#### Success Response (200)
- **message** (string) - Confirmation message including file path or URL.

#### Response Example
{
  "message": "Success. File saved as: ~/Desktop/audio/t2a_sample.mp3"
}
```

--------------------------------

### Generate Images from Text

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Creates images based on text prompts with support for batch generation, custom aspect ratios, and prompt optimization.

```json
{
    "model": "image-01",
    "prompt": "Cyberpunk street scene with rain and neon reflections, highly detailed",
    "aspect_ratio": "16:9",
    "n": 4,
    "prompt_optimizer": true,
    "output_directory": "~/Desktop/images"
}
```

--------------------------------

### POST list_voices

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Retrieves a list of available voices for synthesis, categorized by type.

```APIDOC
## POST list_voices

### Description
Retrieve all available voices for text-to-speech synthesis, including system-provided voices and custom cloned voices.

### Method
POST

### Endpoint
list_voices

### Parameters
#### Request Body
- **voice_type** (string) - Required - Filter by 'all', 'system', or 'voice_cloning'.

### Request Example
{
  "voice_type": "all"
}

### Response
#### Success Response (200)
- **voices** (array) - List of available voice objects.

#### Response Example
{
  "voices": ["Name: Female Shaonv, ID: female-shaonv", "Name: MyClonedVoice, ID: custom_voice_001"]
}
```

--------------------------------

### Configure MiniMax MCP Server

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

JSON configuration for integrating the MiniMax MCP server into an MCP client's settings file. It requires an API key and supports custom base paths and resource delivery modes.

```json
{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": ["minimax-mcp"],
      "env": {
        "MINIMAX_API_KEY": "your-api-key-here",
        "MINIMAX_MCP_BASE_PATH": "~/Desktop",
        "MINIMAX_API_HOST": "https://api.minimax.io",
        "MINIMAX_API_RESOURCE_MODE": "url"
      }
    }
  }
}
```

--------------------------------

### Generate Music Tracks

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Produces AI-generated music based on prompts and lyrics. Supports advanced audio settings like sample rate, bitrate, and format selection.

```json
{
    "prompt": "Emotional ballad, piano-driven, melancholic mood, rainy night atmosphere",
    "lyrics": "[Intro]\n(Soft piano intro)\n[Verse]\nMemories fade like morning dew\nI still remember loving you",
    "sample_rate": 44100,
    "bitrate": 256000,
    "format": "wav",
    "output_directory": "~/Desktop/music"
}
```

--------------------------------

### Generate Video using MiniMax MCP

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Executes video generation tasks using various models like T2V-01 or MiniMax-Hailuo-02. Supports text-to-video, image-to-video, director-style camera controls, and asynchronous processing.

```json
{
    "model": "T2V-01",
    "prompt": "A serene mountain landscape at sunset with clouds drifting slowly across the sky",
    "output_directory": "~/Desktop/videos"
}
```

```json
{
    "model": "MiniMax-Hailuo-02",
    "prompt": "Ocean waves crashing on a rocky coastline at dawn",
    "async_mode": true
}
```

--------------------------------

### Query Video Generation Status

Source: https://context7.com/minimax-ai/minimax-mcp/llms.txt

Checks the status of an asynchronous video generation task using a task ID. Returns the file path if completed or a processing status message.

```json
{
    "task_id": "task_abc123",
    "output_directory": "~/Desktop/videos"
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.