
Claude Desktop
桌面端 · 免费增值 · Proprietary
Anthropic 官方推出的 Claude AI 桌面应用程序。支持 MCP 服务器以扩展功能。

MiniMax-AI/MiniMax-MCP-JS
MiniMax MCP JS是一个JavaScript/TypeScript实现的MiniMax模型上下文协议工具包,提供文本转语音、图像生成、视频生成和语音克隆等功能,支持多种配置方式和传输模式。
npx -y minimax-mcp-js{
"mcpServers": {
"minimax-mcp-js": {
"command": "npx",
"args": [
"-y",
"minimax-mcp-js"
],
"env": {
"MINIMAX_API_HOST": "<MINIMAX_API_HOST>",
"MINIMAX_API_KEY": "<MINIMAX_API_KEY>",
"MINIMAX_MCP_BASE_PATH": "<MINIMAX_MCP_BASE_PATH>",
"MINIMAX_RESOURCE_MODE": "<MINIMAX_RESOURCE_MODE>"
}
}
}
}MINIMAX_API_HOSTMINIMAX_API_KEYMINIMAX_MCP_BASE_PATHMINIMAX_RESOURCE_MODEvoice_design
Generate personalized voices from text descriptions
generate_video
Now supports MiniMax-Hailuo-02 with 6s/10s duration and 768P/1080P resolution options
model
Model version, options are 'speech-02-hd', 'speech-02-turbo', 'speech-01-hd', 'speech-01-turbo', 'speech-01-240228', 'speech-01-turbo-240228', default is…
voiceId
Voice ID, default is 'male-qn-qingse'
speed
Speech speed, range 0.5-2.0, default is 1.0
vol
Volume, range 0.1-10.0, default is 1.0
pitch
Pitch, range -12 to 12, default is 0
emotion
Emotion, options are 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised', 'neutral', default is 'happy'.
format
Audio format, options are 'mp3', 'pcm', 'flac', 'wav', default is 'mp3'
sampleRate
Sample rate (Hz), options are 8000, 16000, 22050, 24000, 32000, 44100, default is 32000
bitrate
Bitrate (bps), options are 64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000, default is 128000
channel
Audio channels, options are 1 or 2, default is 1
languageBoost
Enhance the ability to recognize specified languages and dialects.
stream
Enable streaming output
subtitleEnable
The parameter controls whether the subtitle service is enabled.
outputDirectory
Directory to save the output file. outputDirectory is relative to MINIMAX_MCP_BASE_PATH (or basePath in config).
outputFile
Path to save the output file (optional, auto-generated if not provided)
inputFilePath
Path to the audio file to play (required)
isUrl
Whether the audio file is a URL, default is false
audioFile
Path to audio file (required)
prompt
Image description (required)
aspectRatio
Aspect ratio, default is '1:1', options are '1:1', '16:9','4:3', '3:2', '2:3', '3:4', '9:16', '21:9'
promptOptimizer
Whether to optimize the prompt, default is true
subjectReference
Path to local image file or public URL for character reference (optional)
asyncMode
Whether to use async mode.
firstFrameImage
Path to first frame image (optional)
duration
The duration of the video.
resolution
The resolution of the video.
taskId
The Task ID to query.
previewText
The text to preview the voice.
本页信息摘自该项目的 README。 查看 README
该服务器 README 中提到的客户端:

elevenlabs/elevenlabs-mcp
ElevenLabs官方MCP服务器,提供文本转语音和音频处理API交互能力

MiniMax-AI/MiniMax-MCP
MiniMax Model Context Protocol (MCP) 是一个官方服务器,支持与强大的文本转语音、视频/图像生成API交互,适用于多种客户端工具如Claude Desktop、Cursor等。

mamertofabian/elevenlabs-mcp-server
ElevenLabs文本转语音MCP服务

shijianzhong/smart-pet-with-mcp
一个基于 MCP(Model Context Protocol)协议的智能宠物伴侣应用,通过语音识别和自然语言处理技术,为宠物主人提供实时互动和服务。 该应用是一个 MCP-Client 应用,可以自主无限搭配 MCP-Server 实现需求。

PsychArch/minimax-mcp-tools
Minimax MCP Tools是一个集成Minimax AI能力的MCP服务器实现,提供图像生成和文本转语音功能。

kvadratni/speech-mcp
Speech MCP 是一个为Goose设计的语音交互扩展,提供实时语音识别、文本转语音和音频可视化功能。