Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax mo...
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Use
mmx# Install npm install -g mmx-cliAuth (persisted to ~/.mmx/credentials.json)
mmx auth login --api-key sk-xxxxx
Or pass per-call
mmx text chat --api-key sk-xxxxx --message "Hello"
Region is auto-detected. Override with
--region global--region cnAlways use these flags in non-interactive (agent/CI) contexts:
| Flag | Purpose |
|---|---|
| Fail fast on missing args instead of prompting |
| Suppress spinners/progress; stdout is pure data |
| Machine-readable JSON output |
| Return task ID immediately (video generation) |
| Preview the API request without executing |
| Skip confirmation prompts |
Chat completion. Default model:
MiniMax-M2.7mmx text chat --message <text> [flags]
| Flag | Type | Description |
|---|---|---|
| string, required, repeatable | Message text. Prefix with |
| string | JSON file with messages array. Use |
| string | System prompt |
| string | Model ID (default: |
| number | Max tokens (default: 4096) |
| number | Sampling temperature (0.0, 1.0] |
| number | Nucleus sampling threshold |
| boolean | Stream tokens (default: on in TTY) |
| string, repeatable | Tool definition JSON or file path |
# Single message mmx text chat --message "user:What is MiniMax?" --output json --quietMulti-turn
mmx text chat
--system "You are a coding assistant."
--message "user:Write fizzbuzz in Python"
--output jsonFrom file
cat conversation.json | mmx text chat --messages-file - --output json
stdout: response text (text mode) or full response object (json mode).
Generate images. Model:
image-01mmx image generate --prompt <text> [flags]
| Flag | Type | Description |
|---|---|---|
| string, required | Image description |
| string | e.g. |
| number | Number of images (default: 1) |
| string | Subject reference: |
| string | Download images to directory |
| string | Filename prefix (default: |
mmx image generate --prompt "A cat in a spacesuit" --output json --quiet # stdout: image URLs (one per line in quiet mode)mmx image generate --prompt "Logo" --n 3 --out-dir ./gen/ --quiet
stdout: saved file paths (one per line)
Generate video. Default model:
MiniMax-Hailuo-2.3mmx video generate --prompt <text> [flags]
| Flag | Type | Description |
|---|---|---|
| string, required | Video description |
| string | |
| string | First frame image |
| string | Webhook URL for completion |
| string | Save video to specific file |
| boolean | Return task ID immediately |
| boolean | Same as |
| number | Polling interval (default: 5) |
# Non-blocking: get task ID mmx video generate --prompt "A robot." --async --quiet # stdout: {"taskId":"..."}Blocking: wait and get file path
mmx video generate --prompt "Ocean waves." --download ocean.mp4 --quiet
stdout: ocean.mp4
Query status of a video generation task.
mmx video task get --task-id <id> [--output json]
Download a completed video by task ID.
mmx video download --file-id <id> [--out <path>]
Text-to-speech. Default model:
speech-2.8-hdmmx speech synthesize --text <text> [flags]
| Flag | Type | Description |
|---|---|---|
| string | Text to synthesize |
| string | Read text from file. Use |
| string | |
| string | Voice ID (default: |
| number | Speed multiplier |
| number | Volume level |
| number | Pitch adjustment |
| string | Audio format (default: |
| number | Sample rate (default: 32000) |
| number | Bitrate (default: 128000) |
| number | Audio channels (default: 1) |
| string | Language boost |
| boolean | Include subtitle timing data |
| string, repeatable | Custom pronunciation |
| string | Add sound effect |
| string | Save audio to file |
| boolean | Stream raw audio to stdout |
mmx speech synthesize --text "Hello world" --out hello.mp3 --quiet # stdout: hello.mp3echo "Breaking news." | mmx speech synthesize --text-file - --out news.mp3
Generate music. Model:
music-2.5mmx music generate --prompt <text> [--lyrics <text>] [flags]
| Flag | Type | Description |
|---|---|---|
| string | Music style description (can be detailed) |
| string | Song lyrics with structure tags. Use |
| string | Read lyrics from file. Use |
| string | Vocal style, e.g. |
| string | Music genre, e.g. folk, pop, jazz |
| string | Mood or emotion, e.g. warm, melancholic, uplifting |
| string | Instruments to feature, e.g. |
| string | Tempo description, e.g. fast, slow, moderate |
| number | Exact tempo in beats per minute |
| string | Musical key, e.g. C major, A minor, G sharp |
| string | Elements to avoid in the generated music |
| string | Use case context, e.g. |
| string | Song structure, e.g. |
| string | Reference tracks or artists, e.g. |
| string | Additional fine-grained requirements |
| boolean | Generate instrumental music (no vocals). Cannot be used with |
| boolean | Embed AI-generated content watermark |
| string | Audio format (default: |
| number | Sample rate (default: 44100) |
| number | Bitrate (default: 256000) |
| string | Save audio to file |
| boolean | Stream raw audio to stdout |
At least one of
--prompt--lyrics# Simple usage mmx music generate --prompt "Upbeat pop" --lyrics "La la la..." --out song.mp3 --quietDetailed prompt with vocal characteristics
mmx music generate --prompt "Warm morning folk"
--vocals "male and female duet, harmonies in chorus"
--instruments "acoustic guitar, piano"
--bpm 95
--lyrics-file song.txt
--out duet.mp3Instrumental (use --instrumental flag)
mmx music generate --prompt "Cinematic orchestral, building tension" --instrumental --out bgm.mp3
Image understanding via VLM. Provide either
--image--file-idmmx vision describe (--image <path-or-url> | --file-id <id>) [flags]
| Flag | Type | Description |
|---|---|---|
| string | Local path or URL (auto base64-encoded) |
| string | Pre-uploaded file ID (skips base64) |
| string | Question about the image (default: |
mmx vision describe --image photo.jpg --prompt "What breed?" --output json
stdout: description text (text mode) or full response (json mode).
Web search via MiniMax.
mmx search query --q <query>
| Flag | Type | Description |
|---|---|---|
| string, required | Search query |
mmx search query --q "MiniMax AI" --output json --quiet
Display Token Plan usage and remaining quotas.
mmx quota show [--output json]
Export all commands as Anthropic/OpenAI-compatible JSON tool schemas:
# All tool-worthy commands (excludes auth/config/update) mmx config export-schemaSingle command
mmx config export-schema --command "video generate"
Use this to dynamically register mmx commands as tools in your agent framework.
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | General error |
| 2 | Usage error (bad flags, missing args) |
| 3 | Authentication error |
| 4 | Quota exceeded |
| 5 | Timeout |
| 10 | Content filter triggered |
# stdout is always clean data — safe to pipe mmx text chat --message "Hi" --output json | jq '.content'stderr has progress/spinners — discard if needed
mmx video generate --prompt "Waves" 2>/dev/null
Chain: generate image → describe it
URL=$(mmx image generate --prompt "A sunset" --quiet) mmx vision describe --image "$URL" --quiet
Async video workflow
TASK=$(mmx video generate --prompt "A robot" --async --quiet | jq -r '.taskId') mmx video task get --task-id "$TASK" --output json mmx video download --task-id "$TASK" --out robot.mp4
CLI flags → environment variables →
~/.mmx/config.json# Persistent config mmx config set --key region --value cn mmx config showEnvironment
export MINIMAX_API_KEY=sk-xxxxx export MINIMAX_REGION=cn
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.