Use mmx to generate text, images, video, speech, music, and perform web search via the MiniMax AI platform.
# Install
npm install -g mmx-cli
# Auth (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 or --region cn.
Always use these flags in non-interactive (agent/CI) contexts:
| Flag | Purpose |
|---|---|
| --- | --- |
--non-interactive | Fail fast on missing args instead of prompting |
--quiet | Suppress spinners/progress; stdout is pure data |
--output json | Machine-readable JSON output |
--async | Return task ID immediately (video generation) |
--dry-run | Preview the API request without executing |
--yes | Skip confirmation prompts |
Chat completion. Default model: MiniMax-M2.7.
mmx text chat --message <text> [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--message | string, required, repeatable | Message text. Prefix with role: to set role (e.g. "system:You are helpful", "user:Hello") |
--messages-file | string | JSON file with messages array. Use - for stdin |
--system | string | System prompt |
--model | string | Model ID (default: MiniMax-M2.7) |
--max-tokens | number | Max tokens (default: 4096) |
--temperature | number | Sampling temperature (0.0, 1.0] |
--top-p | number | Nucleus sampling threshold |
--stream | boolean | Stream tokens (default: on in TTY) |
--tool | string, repeatable | Tool definition JSON or file path |
# Single message
mmx text chat --message "user:What is MiniMax?" --output json --quiet
# Multi-turn
mmx text chat \
--system "You are a coding assistant." \
--message "user:Write fizzbuzz in Python" \
--output json
# From 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-01.
mmx image generate --prompt <text> [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--prompt | string, required | Image description |
--aspect-ratio | string | e.g. 16:9, 1:1 |
--n | number | Number of images (default: 1) |
--subject-ref | string | Subject reference: type=character,image=path-or-url |
--out-dir | string | Download images to directory |
--out-prefix | string | Filename prefix (default: image) |
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-2.3. This is an async task — by default it polls until completion.
mmx video generate --prompt <text> [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--prompt | string, required | Video description |
--model | string | MiniMax-Hailuo-2.3 (default) or MiniMax-Hailuo-2.3-Fast |
--first-frame | string | First frame image |
--callback-url | string | Webhook URL for completion |
--download | string | Save video to specific file |
--async | boolean | Return task ID immediately |
--no-wait | boolean | Same as --async |
--poll-interval | 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-hd. Max 10k chars.
mmx speech synthesize --text <text> [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--text | string | Text to synthesize |
--text-file | string | Read text from file. Use - for stdin |
--model | string | speech-2.8-hd (default), speech-2.6, speech-02 |
--voice | string | Voice ID (default: English_expressive_narrator) |
--speed | number | Speed multiplier |
--volume | number | Volume level |
--pitch | number | Pitch adjustment |
--format | string | Audio format (default: mp3) |
--sample-rate | number | Sample rate (default: 32000) |
--bitrate | number | Bitrate (default: 128000) |
--channels | number | Audio channels (default: 1) |
--language | string | Language boost |
--subtitles | boolean | Include subtitle timing data |
--pronunciation | string, repeatable | Custom pronunciation |
--sound-effect | string | Add sound effect |
--out | string | Save audio to file |
--stream | boolean | Stream raw audio to stdout |
mmx speech synthesize --text "Hello world" --out hello.mp3 --quiet
# stdout: hello.mp3
echo "Breaking news." | mmx speech synthesize --text-file - --out news.mp3
Generate music. Model: music-2.5. Responds well to rich, structured descriptions.
mmx music generate --prompt <text> [--lyrics <text>] [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--prompt | string | Music style description (can be detailed) |
--lyrics | string | Song lyrics with structure tags. Use "\u65e0\u6b4c\u8bcd" for instrumental. Cannot be used with --instrumental |
--lyrics-file | string | Read lyrics from file. Use - for stdin |
--vocals | string | Vocal style, e.g. "warm male baritone", "bright female soprano", "duet with harmonies" |
--genre | string | Music genre, e.g. folk, pop, jazz |
--mood | string | Mood or emotion, e.g. warm, melancholic, uplifting |
--instruments | string | Instruments to feature, e.g. "acoustic guitar, piano" |
--tempo | string | Tempo description, e.g. fast, slow, moderate |
--bpm | number | Exact tempo in beats per minute |
--key | string | Musical key, e.g. C major, A minor, G sharp |
--avoid | string | Elements to avoid in the generated music |
--use-case | string | Use case context, e.g. "background music for video", "theme song" |
--structure | string | Song structure, e.g. "verse-chorus-verse-bridge-chorus" |
--references | string | Reference tracks or artists, e.g. "similar to Ed Sheeran" |
--extra | string | Additional fine-grained requirements |
--instrumental | boolean | Generate instrumental music (no vocals). Cannot be used with --lyrics or --lyrics-file |
--aigc-watermark | boolean | Embed AI-generated content watermark |
--format | string | Audio format (default: mp3) |
--sample-rate | number | Sample rate (default: 44100) |
--bitrate | number | Bitrate (default: 256000) |
--out | string | Save audio to file |
--stream | boolean | Stream raw audio to stdout |
At least one of --prompt or --lyrics is required.
# Simple usage
mmx music generate --prompt "Upbeat pop" --lyrics "La la la..." --out song.mp3 --quiet
# Detailed 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.mp3
# Instrumental (use --instrumental flag)
mmx music generate --prompt "Cinematic orchestral, building tension" --instrumental --out bgm.mp3
Image understanding via VLM. Provide either --image or --file-id, not both.
mmx vision describe (--image <path-or-url> | --file-id <id>) [flags]
| Flag | Type | Description |
|---|---|---|
| --- | --- | --- |
--image | string | Local path or URL (auto base64-encoded) |
--file-id | string | Pre-uploaded file ID (skips base64) |
--prompt | string | Question about the image (default: "Describe the image.") |
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 |
|---|---|---|
| --- | --- | --- |
--q | 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-schema
# Single 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 → defaults.
# Persistent config
mmx config set --key region --value cn
mmx config show
# Environment
export MINIMAX_API_KEY=sk-xxxxx
export MINIMAX_REGION=cn
共 1 个版本