Use MiniMax for web search, image understanding, image generation, and speech synthesis.
Feature 1: Web Search
Call web_search
Use a script to call the MCP service:
python3 {curDir}/scripts/web_search.py "<搜索查询>"
Example:
# 搜索今日新闻
python3 {curDir}/scripts/web_search.py "今天的热点新闻"
API Parameter Description
| Parameter | Description | Type |
|---|---|---|
| query | Search query string | string (required) |
Feature 2: Image Understanding
Prepare the image
Place the image in an accessible path, for example:
~/.openclaw/workspace/images/图片名.jpg- Or use a URL
Call understand_image
Use a script to call the MCP service:
python3 {curDir}/scripts/understand_image.py <图片路径或URL> "<对图片的提问>"
Example:
# 描述图片内容
python3 {curDir}/scripts/understand_image.py ~/image.jpg "详细描述这张图片的内容"
# 使用 URL
python3 {curDir}/scripts/understand_image.py "https://example.com/image.jpg" "这张图片展示了什么?"
API Parameter Description
| Parameter | Description | Type |
|---|---|---|
| image | Image path or URL | string (required) |
| prompt | Question about the image | string (required) |
Feature 3: Image Generation
Note: Image generation consumes a large number of tokens. Before executing, you must first ask the user whether they agree to generate.
Call image
Use a script to call the MiniMax image generation API:
python3 {curDir}/scripts/image.py "<描述>" [选项]
Example:
# 文生图(T2I)
python3 {curDir}/scripts/image.py "一只可爱的猫咪在阳光下玩耍"
# 指定宽高比和数量
python3 {curDir}/scripts/image.py "一只可爱的猫咪在阳光下玩耍" --aspect-ratio 16:9 --n 2
# 指定宽高
python3 {curDir}/scripts/image.py "一只可爱的猫咪在阳光下玩耍" --width 1024 --height 768 --output cat.png
# 图生图(I2I)
python3 {curDir}/scripts/image.py --subject /path/to/image.jpg "猫咪玩耍"
Option Description
| Option | Description | Default Value |
|---|---|---|
| --model | Model version | image-01 |
| --aspect-ratio | Image aspect ratio | 1:1 |
| --width | Image width (512-2048, multiple of 8) | None |
| --height | Image height (512-2048, multiple of 8) | None |
| --n | Number of images to generate (1-9) | 1 |
| --seed | Random seed | None |
| --output | Save the image to a file (png/jpg format) | None |
| --subject | Subject reference image (image-to-image I2I) | None |
Available Models
Text-to-image (T2I):
- image-01
- image-01-live
Image-to-image (I2I):
- image-01
- image-01-live
Aspect Ratio Options
- 1:1 (1024x1024)
- 16:9 (1280x720)
- 4:3 (1152x864)
- 3:2 (1248x832)
- 2:3 (832x1248)
- 3:4 (864x1152)
- 9:16 (720x1280)
- 21:9 (1344x576) (only applicable to image-01)
Feature 4: Speech Synthesis (Text-to-Speech)
Call text_to_speech
Use a script to call the MiniMax speech synthesis API:
python3 {curDir}/scripts/text_to_speech.py "<文本>" [选项]
Example:
# 基础语音合成
python3 {curDir}/scripts/text_to_speech.py "你好世界" --output audio.mp3
# 指定音色和情感
python3 {curDir}/scripts/text_to_speech.py "今天真开心" --voice female-shaonv --emotion happy --output happy.mp3
# 列出所有可用音色
python3 {curDir}/scripts/text_to_speech.py --list-voices
Option Description
| Option | Description | Default Value |
|---|---|---|
| --model | Model version | speech-2.8-hd |
| --output | Save the audio to a file (mp3 format) | None (directly outputs JSON containing hexadecimal data) |
| --voice | Voice ID | female-shaonv |
| --emotion | Emotion (happy, sad, angry, fearful, disgusted, surprised, calm, fluent, whisper) | None |
| --list-voices | List all available voice options | None |