minimax

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

MiniMax API

Use the MiniMax API via direct

curl

calls for AI chat completion, text-to-speech, and video generation.

Official docs:
https://platform.minimax.io/docs

通过直接调用

curl

来使用MiniMax API，实现AI对话补全、文本转语音和视频生成功能。

官方文档：
https://platform.minimax.io/docs

When to Use

适用场景

Use this skill when you need to:

Chat completion with Chinese-optimized LLM (MiniMax-M1/M2)
Text-to-speech with natural voices and emotion control
Video generation from text prompts (T2V)
Image-to-video conversion (I2V)

在以下场景中可使用该技能：

使用针对中文优化的大模型（MiniMax-M1/M2）进行对话补全
生成带有自然音色和情绪控制的文本转语音内容
通过文本提示生成视频（T2V）
实现图转视频（I2V）转换

Prerequisites

前置条件

Sign up at MiniMax Platform
Go to Account Management > API Keys to create an API key
Note: Global users should use
```
api.minimaxi.chat
```
(with extra "i")

bash

export MINIMAX_API_KEY="your-api-key"

在MiniMax平台注册账号
进入“账号管理 > API密钥”页面创建API密钥
注意：全球用户请使用
```
api.minimaxi.chat
```
（多一个字母"i"）

bash

export MINIMAX_API_KEY="your-api-key"

API Hosts

API主机地址

Region	Base URL
China	`https://api.minimax.io`
Global	`https://api.minimaxi.chat`

Important: When using
$VAR
in a command that pipes to another command, wrap the command containing
$VAR
in
bash -c '...'
. Due to a Claude Code bug, environment variables are silently cleared when pipes are used directly.
bash
bash -c 'curl -s "https://api.example.com" -H "Authorization: Bearer $API_KEY"'

地区	基础URL
中国	`https://api.minimax.io`
全球	`https://api.minimaxi.chat`

重要提示： 当在包含管道操作的命令中使用
$VAR
时，请将包含
$VAR
的命令用
bash -c '...'
包裹。由于Claude Code的bug，直接使用管道时环境变量会被自动清除。
bash
bash -c 'curl -s "https://api.example.com" -H "Authorization: Bearer $API_KEY"'

How to Use

使用方法

All examples below assume you have

MINIMAX_API_KEY

set.

Authentication uses Bearer token in the

Authorization

header.

以下所有示例均假设你已设置好

MINIMAX_API_KEY

环境变量。

认证方式为在

Authorization

请求头中携带Bearer令牌。

1. Basic Chat Completion

1. 基础对话补全

Send a chat message:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello, who are you?"}
  ]
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0].message.content'

Available models:

```
MiniMax-M2
```
: Reasoning model (best quality)
```
MiniMax-M1
```
: Reasoning model (balanced)
```
MiniMax-Text-01
```
: Standard model (fastest)

发送对话消息：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello, who are you?"}
  ]
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0].message.content'

可用模型：

```
MiniMax-M2
```
：推理模型（质量最佳）
```
MiniMax-M1
```
：推理模型（性能均衡）
```
MiniMax-Text-01
```
：标准模型（速度最快）

2. Chat with Temperature Control

2. 带温度控制的对话

Adjust creativity:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "user", "content": "Write a short poem about AI."}
  ],
  "temperature": 0.7,
  "max_tokens": 200
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0].message.content'

Parameters:

```
temperature
```
(0-1): Higher = more creative
```
top_p
```
(0-1, default 0.95): Sampling diversity
```
max_tokens
```
: Maximum output tokens

调整生成内容的创意度：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "user", "content": "Write a short poem about AI."}
  ],
  "temperature": 0.7,
  "max_tokens": 200
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0].message.content'

参数说明：

```
temperature
```
（0-1）：数值越高，生成内容越具创意
```
top_p
```
（0-1，默认0.95）：采样多样性
```
max_tokens
```
：最大输出令牌数

3. Streaming Response

3. 流式响应

Get real-time output:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-M1",
  "messages": [
    {"role": "user", "content": "Explain quantum computing."}
  ],
  "stream": true
}

Then run:

bash

curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json

Streaming is recommended for reasoning models (M1/M2).

获取实时输出：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-M1",
  "messages": [
    {"role": "user", "content": "Explain quantum computing."}
  ],
  "stream": true
}

然后执行命令：

bash

curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json

推理模型（M1/M2）推荐使用流式响应。

4. Reasoning Model (M1/M2)

4. 推理模型（M1/M2）

Use reasoning models for complex tasks:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-M1",
  "messages": [
    {"role": "user", "content": "Solve step by step: A train travels 120km in 2 hours. What is its average speed in m/s?"}
  ],
  "stream": true
}

Then run:

bash

curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json

Response includes

reasoning_content

field with thought process.

使用推理模型处理复杂任务：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-M1",
  "messages": [
    {"role": "user", "content": "Solve step by step: A train travels 120km in 2 hours. What is its average speed in m/s?"}
  ],
  "stream": true
}

然后执行命令：

bash

curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json

响应结果包含

reasoning_content

字段，展示模型的思考过程。

5. Text-to-Speech (Basic)

5. 基础文本转语音（TTS）

Convert text to speech:

Write to

/tmp/minimax_request.json

json

{
  "model": "speech-02-hd",
  "text": "Hello, this is a test of MiniMax text to speech.",
  "voice_id": "male-qn-qingse",
  "speed": 1.0,
  "format": "mp3"
}

Then run:

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output speech.mp3

将文本转换为语音：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "speech-02-hd",
  "text": "Hello, this is a test of MiniMax text to speech.",
  "voice_id": "male-qn-qingse",
  "speed": 1.0,
  "format": "mp3"
}

然后执行命令：

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output speech.mp3

6. TTS with Emotion

6. 带情绪的文本转语音

Add emotion to speech (speech-02 models):

Write to

/tmp/minimax_request.json

json

{
  "model": "speech-02-hd",
  "text": "I am so happy to meet you today!",
  "voice_id": "female-shaonv",
  "emotion": "happy",
  "speed": 1.0,
  "format": "mp3"
}

Then run:

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output happy_speech.mp3

Emotion options:

happy

sad

angry

fearful

disgusted

surprised

neutral

为语音添加情绪（仅支持speech-02系列模型）：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "speech-02-hd",
  "text": "I am so happy to meet you today!",
  "voice_id": "female-shaonv",
  "emotion": "happy",
  "speed": 1.0,
  "format": "mp3"
}

然后执行命令：

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output happy_speech.mp3

可选情绪：

happy

（开心）、

sad

（悲伤）、

angry

（愤怒）、

fearful

（恐惧）、

disgusted

（厌恶）、

surprised

（惊讶）、

neutral

（中性）

7. TTS with Audio Settings

7. 自定义音频设置的文本转语音

Fine-tune audio output:

Write to

/tmp/minimax_request.json

json

{
  "model": "speech-02-hd",
  "text": "High quality audio test.",
  "voice_id": "male-qn-qingse",
  "speed": 1.0,
  "vol": 1.0,
  "pitch": 0,
  "audio_sample_rate": 32000,
  "bitrate": 128000,
  "format": "mp3"
}

Then run:

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output hq_speech.mp3

TTS models:

```
speech-02-hd
```
: High definition (best quality)
```
speech-02-turbo
```
: Fast generation
```
speech-01-hd
```
: Previous gen HD
```
speech-01-turbo
```
: Previous gen fast

微调音频输出效果：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "speech-02-hd",
  "text": "High quality audio test.",
  "voice_id": "male-qn-qingse",
  "speed": 1.0,
  "vol": 1.0,
  "pitch": 0,
  "audio_sample_rate": 32000,
  "bitrate": 128000,
  "format": "mp3"
}

然后执行命令：

bash

curl -s "https://api.minimax.io/v1/t2a_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json --output hq_speech.mp3

TTS模型：

```
speech-02-hd
```
：高清模型（质量最佳）
```
speech-02-turbo
```
：快速生成模型
```
speech-01-hd
```
：上一代高清模型
```
speech-01-turbo
```
：上一代快速生成模型

8. Text-to-Video (T2V)

8. 文本转视频（T2V）

Generate video from text prompt:

Write to

/tmp/minimax_request.json

json

{
  "model": "T2V-01-Director",
  "prompt": "A cat playing with a ball of yarn [Static shot].",
  "duration": 6,
  "resolution": "1080P"
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

Video generation is async - returns a task ID to poll for completion.

通过文本提示生成视频：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "T2V-01-Director",
  "prompt": "A cat playing with a ball of yarn [Static shot].",
  "duration": 6,
  "resolution": "1080P"
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

视频生成为异步操作，返回任务ID用于轮询生成进度。

9. T2V with Camera Control

9. 带镜头控制的文本转视频

Control camera movement in videos:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "A person walking through a forest [Tracking shot], then stops to look at a bird [Push in].",
  "duration": 6,
  "resolution": "1080P"
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

Camera commands (in brackets):

Movement:

Truck left/right

Pan left/right

Push in/Pull out

Vertical:
```
Pedestal up/down
```
,
```
Tilt up/down
```
Zoom:
```
Zoom in/out
```
Special:
```
Shake
```
,
```
Tracking shot
```
,
```
Static shot
```

Combine with

[Pan left, Pedestal up]

(max 3 simultaneous).

控制视频中的镜头运动：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "A person walking through a forest [Tracking shot], then stops to look at a bird [Push in].",
  "duration": 6,
  "resolution": "1080P"
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

镜头命令（放在方括号中）：

移动类：
```
Truck left/right
```
（左右平移）、
```
Pan left/right
```
（左右摇镜）、
```
Push in/Pull out
```
（推镜/拉镜）
垂直类：
```
Pedestal up/down
```
（上下升降）、
```
Tilt up/down
```
（上下俯仰）
缩放类：
```
Zoom in/out
```
（放大/缩小）
特殊类：
```
Shake
```
（震动）、
```
Tracking shot
```
（跟拍）、
```
Static shot
```
（固定镜头）

可组合多个命令，格式如

[Pan left, Pedestal up]

（最多同时使用3个）。

10. Image-to-Video (I2V)

10. 图转视频（I2V）

Generate video from an image:

Note: For I2V, use
MiniMax-Hailuo-2.3
or
S2V-01
model which supports
first_frame_image
. The
T2V-01-Director
model is text-to-video only.

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "The scene comes to life with gentle movement [Static shot].",
  "first_frame_image": "https://example.com/image.jpg",
  "duration": 6,
  "resolution": "1080P"
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

Provide

first_frame_image

as URL or base64-encoded image.

通过图片生成视频：

注意： 图转视频功能需使用支持
first_frame_image
参数的
MiniMax-Hailuo-2.3
或
S2V-01
模型。
T2V-01-Director
模型仅支持文本转视频。

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "The scene comes to life with gentle movement [Static shot].",
  "first_frame_image": "https://example.com/image.jpg",
  "duration": 6,
  "resolution": "1080P"
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/video_generation" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.task_id'

first_frame_image

参数可传入图片URL或base64编码的图片内容。

11. Function Calling (Tools)

11. 函数调用（工具）

Use tools with chat:

Write to

/tmp/minimax_request.json

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "user", "content": "What is the weather in Beijing?"}
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"}
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}

Then run:

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0]'

在对话中调用工具：

写入内容到

/tmp/minimax_request.json

：

json

{
  "model": "MiniMax-Text-01",
  "messages": [
    {"role": "user", "content": "What is the weather in Beijing?"}
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"}
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}

然后执行命令：

bash

bash -c 'curl -s "https://api.minimax.io/v1/text/chatcompletion_v2" -X POST -H "Authorization: Bearer ${MINIMAX_API_KEY}" -H "Content-Type: application/json" -d @/tmp/minimax_request.json' | jq '.choices[0]'

Response Format

响应格式

Chat Completion

对话补全

json

{
  "id": "string",
  "choices": [{
  "message": {
  "role": "assistant",
  "content": "Response text",
  "reasoning_content": "Thought process (M1/M2 only)"
  },
  "finish_reason": "stop"
  }],
  "usage": {
  "prompt_tokens": 10,
  "completion_tokens": 50,
  "total_tokens": 60
  }
}

json

{
  "id": "string",
  "choices": [{
  "message": {
  "role": "assistant",
  "content": "Response text",
  "reasoning_content": "Thought process (M1/M2 only)"
  },
  "finish_reason": "stop"
  }],
  "usage": {
  "prompt_tokens": 10,
  "completion_tokens": 50,
  "total_tokens": 60
  }
}

Guidelines

注意事项

Use correct host: China uses
```
api.minimax.io
```
, global uses
```
api.minimaxi.chat
```
Streaming for reasoning: M1/M2 models work best with
```
stream: true
```
Camera syntax: Video commands go in
```
[brackets]
```
within prompts
Emotion in TTS: Only works with
```
speech-02-*
```
and
```
speech-01-*
```
models
Async video: Video generation returns task ID - poll for completion
Chinese optimized: MiniMax excels at Chinese language tasks

使用正确的主机地址：中国地区使用
```
api.minimax.io
```
，全球用户使用
```
api.minimaxi.chat
```
推理模型推荐流式响应：M1/M2模型配合
```
stream: true
```
使用效果最佳
镜头命令语法：视频镜头命令需放在提示词的
```
[方括号]
```
中
TTS情绪支持：仅
```
speech-02-*
```
和
```
speech-01-*
```
模型支持情绪设置
视频生成异步处理：视频生成返回任务ID，需轮询获取生成结果
中文优化：MiniMax模型在中文语言任务上表现优异