resolution
The resolution of the video. The model must be "MiniMax-Hailuo-02". Values range ["768P", "1080P"]. (optional)
How to use it
resolution is exposed by the MiniMax MCP JS MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the resolution tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install MiniMax MCP JS
npx -y @smithery/cli install @MiniMax-AI/MiniMax-MCP-JS --client claudeOther tools in MiniMax MCP JS (32)
Aspect ratio, default is '1:1', options are '1:1', '16:9','4:3', '3:2', '2:3', '3:4', '9:16', '21:9'
Whether to use async mode. Defaults to False. If True, the video generation task will be submitted asynchronously and the response will return a taskid. Should use queryvideogeneration tool to check the status of the task and get the result. (optional)
Path to audio file (required)
Bitrate (bps), options are 64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000, default is 128000
Audio channels, options are 1 or 2, default is 1
The duration of the video. The model must be "MiniMax-Hailuo-02". Values can be 6 and 10. (optional)
Emotion, options are 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised', 'neutral', default is 'happy'. Note: This parameter only works with 'speech-02-hd', 'speech-02-turbo', 'speech-01-turbo', 'speech-01-hd' models
Path to first frame image (optional)
Audio format, options are 'mp3', 'pcm', 'flac', 'wav', default is 'mp3'
Now supports MiniMax-Hailuo-02 with 6s/10s duration and 768P/1080P resolution options
Path to the audio file to play (required)
Whether the audio file is a URL, default is false
Enhance the ability to recognize specified languages and dialects.
Song lyrics for music generation. Use newline (\\n) to separate each line of lyrics. Supports lyric structure tags [Intro] [Verse] [Chorus] [Bridge] [Outro] to enhance musicality. Character range: [10, 600] (each Chinese character, punctuation, and letter counts as 1 character). (required)
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 'speech-02-hd'
High-quality music creation with music-1.5 model
Directory to save the output file. outputDirectory is relative to MINIMAXMCPBASEPATH (or basePath in config). The final save path is ${basePath}/${outputDirectory}. For example, if MINIMAXMCPBASEPATH=~/Desktop and outputDirectory=workspace, the output will be saved to ~/Desktop/workspace/. (optional
Path to save the output file (optional, auto-generated if not provided)
Pitch, range -12 to 12, default is 0
The text to preview the voice. (required)
Image description (required)
Whether to optimize the prompt, default is true
Sample rate (Hz), options are 8000, 16000, 22050, 24000, 32000, 44100, default is 32000
Speech speed, range 0.5-2.0, default is 1.0
Enable streaming output
Path to local image file or public URL for character reference (optional)
The parameter controls whether the subtitle service is enabled. The model must be 'speech-01-turbo' or 'speech-01-hd'. If this parameter is not provided, the default value is false
The Task ID to query. Should be the taskid returned by generatevideo tool if asyncmode is True. (required)
Text to convert (required)
Generate personalized voices from text descriptions
Voice ID, default is 'male-qn-qingse'
Volume, range 0.1-10.0, default is 1.0