MiniMax Multi-Modal Toolkit

Prerequisites

brew install ffmpeg jq              # macOS (or apt install ffmpeg jq on Linux)
bash scripts/check_environment.sh

No Python or pip required — all scripts are pure bash using curl, ffmpeg, jq, and xxd.

API Host Configuration

MiniMax provides two service endpoints for different regions. Set MINIMAX_API_HOST before running any script:

# China Mainland
export MINIMAX_API_HOST="https://api.minimaxi.com"

# or Global
export MINIMAX_API_HOST="https://api.minimax.io"

IMPORTANT — When API Host is missing: Before running any script, check if MINIMAX_API_HOST is set in the environment. If it is NOT configured:

1. Ask the user which service endpoint their MiniMax account uses:
   • China Mainland → https://api.minimaxi.com
   • Global → https://api.minimax.io
2. Instruct and help user to set it via export MINIMAX_API_HOST="https://api.minimaxi.com" (or the global variant) in their terminal or add it to their shell profile (~/.zshrc / ~/.bashrc) for persistence

API Key Configuration

Set the MINIMAX_API_KEY environment variable before running any script:

export MINIMAX_API_KEY="your-api-key-here"

The key starts with sk-api- or sk-cp-, obtainable from https://platform.minimaxi.com (China) or https://platform.minimax.io (Global)

IMPORTANT — When API Key is missing: Before running any script, check if MINIMAX_API_KEY is set in the environment. If it is NOT configured:

1. Ask the user to provide their MiniMax API key
2. Instruct and help user to set it via export MINIMAX_API_KEY="sk-..." in their terminal or add it to their shell profile (~/.zshrc / ~/.bashrc) for persistence

Plan Limits & Quotas

IMPORTANT — Always respect the user's plan limits before generating content. If the user's quota is exhausted or insufficient, warn them before proceeding.

Standard Plans

High-Speed Plans

Key quota constraints:

• Video resolution: 768P only — 1080P is not available on any plan
• Video duration: 6s — all plan quotas are counted in 6-second units
• Video quota is very limited (2–5/day depending on plan) — always confirm with the user before generating video

Key Capabilities

TTS (Text-to-Speech)

Entry point: scripts/tts/generate_voice.sh

IMPORTANT: Single voice vs Multi-segment — Choose the right approach

Default behavior: When the user simply asks to generate speech/voice and does NOT mention multiple voices or characters, use the tts command directly with a single appropriate voice. Do NOT split into segments or use the multi-segment pipeline — just pass the full text to tts in one call.

Only use multi-segment generate when:

• The user explicitly needs multiple voices/characters
• The text requires narrator + character dialogue separation
• The text exceeds 10,000 characters (API limit per request) — in this case, split into segments with the same voice

Single-voice generation (DEFAULT)

bash scripts/tts/generate_voice.sh tts "Hello world" -o ~/.openclaw/openclaw-data/multimodal/outputs/hello.mp3
bash scripts/tts/generate_voice.sh tts "你好世界" -v female-shaonv -o ~/.openclaw/openclaw-data/multimodal/outputs/hello_cn.mp3

Multi-segment generation (multi-voice / audiobook / podcast)

Complete workflow — follow ALL steps in order:

1. Write segments.json — split text into segments with voice assignments (see format and rules below)
2. Run generate command — this reads segments.json, generates audio for EACH segment via TTS API, then merges them into a single output file with crossfade

# Step 1: Write segments.json to ~/.openclaw/openclaw-data/multimodal/outputs/
# (use the Write tool to create ~/.openclaw/openclaw-data/multimodal/outputs/segments.json)

# Step 2: Generate audio from segments.json — this is the CRITICAL step
# It generates each segment individually and merges them into one file
bash scripts/tts/generate_voice.sh generate ~/.openclaw/openclaw-data/multimodal/outputs/segments.json \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/output.mp3 --crossfade 200

Do NOT skip Step 2. Writing segments.json alone does nothing — you MUST run the generate command to actually produce audio.

Voice management

# List all available voices
bash scripts/tts/generate_voice.sh list-voices

# Voice cloning (from audio sample, 10s–5min)
bash scripts/tts/generate_voice.sh clone sample.mp3 --voice-id my-voice

# Voice design (from text description)
bash scripts/tts/generate_voice.sh design "A warm female narrator voice" --voice-id narrator

Audio processing

bash scripts/tts/generate_voice.sh merge part1.mp3 part2.mp3 -o ~/.openclaw/openclaw-data/multimodal/outputs/combined.mp3
bash scripts/tts/generate_voice.sh convert input.wav -o ~/.openclaw/openclaw-data/multimodal/outputs/output.mp3

TTS Models

segments.json Format

Default crossfade between segments: 200ms (--crossfade 200).

[
  { "text": "Hello!", "voice_id": "female-shaonv", "emotion": "" },
  { "text": "Welcome.", "voice_id": "male-qn-qingse", "emotion": "happy" }
]

Leave emotion empty for speech-2.8 models (auto-matched from text).

IMPORTANT: Multi-Segment Script Generation Rules (Audiobooks, Podcasts, etc.)

When generating segments.json for audiobooks, podcasts, or any multi-character narration, you MUST split narration text from character dialogue into separate segments with distinct voices.

Rule: Narration and dialogue are ALWAYS separate segments.

A sentence like "Tom said: The weather is great today!" must be split into two segments:

• Segment 1 (narrator voice): "Tom said:"
• Segment 2 (character voice): "The weather is great today!"

Example — Audiobook with narrator + 2 characters:

[
  { "text": "Morning sunlight streamed into the classroom as students filed in one by one.", "voice_id": "narrator-voice", "emotion": "" },
  { "text": "Tom smiled and turned to Lisa:", "voice_id": "narrator-voice", "emotion": "" },
  { "text": "The weather is amazing today! Let's go to the park after school!", "voice_id": "tom-voice", "emotion": "happy" },
  { "text": "Lisa thought for a moment, then replied:", "voice_id": "narrator-voice", "emotion": "" },
  { "text": "Sure, but I need to drop off my backpack at home first.", "voice_id": "lisa-voice", "emotion": "" },
  { "text": "They exchanged a smile and went back to listening to the lecture.", "voice_id": "narrator-voice", "emotion": "" }
]

Key principles:

1. Narrator uses a consistent neutral narrator voice throughout
2. Each character has a dedicated voice_id, maintained consistently across all their dialogue
3. Split at dialogue boundaries — "He said:" is narrator, the quoted content is the character
4. Do NOT merge narrator text and character speech into a single segment
5. For characters without pre-existing voice_ids, use voice cloning or voice design to create them first, then reference the created voice_id in segments

Music Generation

Entry point: scripts/music/generate_music.sh

IMPORTANT: Instrumental vs Lyrics — When to use which

When adding background music to video or voice content, always default to instrumental mode (--instrumental). Do not ask the user — BGM should never have vocals competing with the main content.

When the user explicitly asks to create/generate music as the primary task, ask them whether they want:

• Instrumental (pure music, no vocals)
• With lyrics (song with vocals — user provides or you help write lyrics)

# Instrumental (for BGM or when user chooses instrumental)
bash scripts/music/generate_music.sh \
  --instrumental \
  --prompt "ambient electronic, atmospheric" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/ambient.mp3 --download

# Song with lyrics (when user chooses vocal music)
bash scripts/music/generate_music.sh \
  --lyrics "[verse]\nHello world\n[chorus]\nLa la la" \
  --prompt "indie folk, melancholic" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/song.mp3 --download

# With style fields
bash scripts/music/generate_music.sh \
  --lyrics "[verse]\nLyrics here" \
  --genre "pop" --mood "upbeat" --tempo "fast" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/pop_track.mp3 --download

Music Model

Default model: music-2.5

music-2.5 does not support --instrumental directly. When instrumental music is needed, the script automatically applies a workaround:

• Sets lyrics to [intro] [outro] (empty structural tags, no actual vocals), appends pure music, no lyrics to the prompt

This produces instrumental-style output without requiring manual intervention. You can always use --instrumental and the script handles the rest.

Image Generation

Entry point: scripts/image/generate_image.sh

Model: image-01 — photorealistic image generation from text prompts, with optional character reference for image-to-image.

IMPORTANT: Mode Selection — t2i vs i2i

Default behavior: When the user asks to generate/create an image without mentioning a reference photo, use t2i mode (default). Only use i2i mode when the user provides a character reference image or explicitly asks to base the image on an existing person's appearance.

IMPORTANT: Aspect Ratio — Infer from user context

Do NOT always default to 1:1. Analyze the user's request and choose the most appropriate aspect ratio:

IMPORTANT: Image Count — When to generate multiple images

Text-to-Image Examples

# Basic text-to-image
bash scripts/image/generate_image.sh \
  --prompt "A cat sitting on a rooftop at sunset, cinematic lighting, warm tones, photorealistic" \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/cat.png

# Landscape with inferred aspect ratio
bash scripts/image/generate_image.sh \
  --prompt "Mountain landscape with misty valleys, photorealistic, golden hour" \
  --aspect-ratio 16:9 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/landscape.png

# Phone wallpaper (portrait 9:16)
bash scripts/image/generate_image.sh \
  --prompt "Aurora borealis over a snowy forest, vivid colors, magical atmosphere" \
  --aspect-ratio 9:16 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/wallpaper.png

# Multiple variations
bash scripts/image/generate_image.sh \
  --prompt "Abstract geometric art, vibrant colors" \
  -n 3 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/art.png

# With prompt optimizer
bash scripts/image/generate_image.sh \
  --prompt "A man standing on Venice Beach, 90s documentary style" \
  --aspect-ratio 16:9 --prompt-optimizer \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/beach.png

# Custom dimensions (must be multiple of 8)
bash scripts/image/generate_image.sh \
  --prompt "Product photo of a luxury watch on marble surface" \
  --width 1024 --height 768 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/watch.png

Image-to-Image (Character Reference)

Use a reference photo to generate images with the same character in new scenes. Best results with a single front-facing portrait. Supported formats: JPG, JPEG, PNG (max 10MB).

# Character reference — place same person in a new scene
bash scripts/image/generate_image.sh \
  --mode i2i \
  --prompt "A girl looking into the distance from a library window, warm afternoon light" \
  --ref-image face.jpg \
  --aspect-ratio 16:9 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/girl_library.png

# Multiple character variations
bash scripts/image/generate_image.sh \
  --mode i2i \
  --prompt "A woman in a red dress at a gala event, elegant, cinematic" \
  --ref-image face.jpg -n 3 \
  -o ~/.openclaw/openclaw-data/multimodal/outputs/gala.png

Aspect Ratio Reference

Key Options

Video Generation

IMPORTANT: Single vs Multi-Segment — Choose the right script

Default behavior: Always use single-segment generate_video.sh with duration 6s and resolution 768P unless the user explicitly asks for a long video or multi-scene video. Do NOT automatically split into multiple segments — a single 6s video is the standard output. Only use generate_long_video.sh when the user clearly needs multi-scene or longer content.

Entry point (single video): scripts/video/generate_video.sh Entry point (long/multi-scene): scripts/video/generate_long_video.sh

Video Model Constraints (MUST follow)

Supported resolutions and durations by model:

Key rules:

• Default: 6s + 768P — plan quotas are counted in 6-second units; use 6s unless user explicitly requests 10s
• 1080P is NOT supported on any plan — always use 768P for Hailuo-2.3/2.3-Fast
• Older models (T2V-01, I2V-01, S2V-01) only support 6s at 720P

IMPORTANT: Prompt Optimization (MUST follow before generating any video)

Before calling any video generation script, you MUST optimize the user's prompt by reading and applying references/video-prompt-guide.md. Never pass the user's raw description directly as --prompt.

Optimization steps:

1. Apply the Professional Formula: Main subject + Scene + Movement + Camera motion + Aesthetic atmosphere

   • BAD: "A puppy in a park"
   • GOOD: "A golden retriever puppy runs toward the camera on a sun-dappled grass path in a park, [跟随] smooth tracking shot, warm golden hour lighting, shallow depth of field, joyful atmosphere"

2. Add camera instructions using [指令] syntax: [推进], [拉远], [跟随], [固定], [左摇], etc.

3. Include aesthetic details: lighting (golden hour, dramatic side lighting), color grading (warm tones, cinematic), texture (dust particles, rain droplets), atmosphere (intimate, epic, peaceful)

4. Keep to 1-2 key actions for 6-10 second videos — do not overcrowd with events

5. For i2v mode (image-to-video): Focus prompt on movement and change only, since the image already establishes the visual. Do NOT re-describe what's in the image.

   • BAD: "A lake with mountains" (just repeating the image)
   • GOOD: "Gentle ripples spread across the water surface, a breeze rustles the distant trees, [固定] fixed camera, soft morning light, peaceful and serene"

6. For multi-segment long videos: Each segment's prompt must be self-contained and optimized individually. The i2v segments (segment 2+) should describe motion/change relative to the previous segment's ending frame.

# Text-to-video (default: 6s, 768P)
bash scripts/video/generate_video.sh \
  --mode t2v \
  --prompt "A golden retriever puppy bounds toward the camera on a sunlit grass path, [跟随] tracking shot, warm golden hour, shallow depth of field, joyful" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/puppy.mp4

# Image-to-video (prompt focuses on MOTION, not image content)
bash scripts/video/generate_video.sh \
  --mode i2v \
  --prompt "The petals begin to sway gently in the breeze, soft light shifts across the surface, [固定] fixed framing, dreamy pastel tones" \
  --first-frame photo.jpg \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/animated.mp4

# Start-end frame interpolation (sef mode uses MiniMax-Hailuo-02)
bash scripts/video/generate_video.sh \
  --mode sef \
  --first-frame start.jpg --last-frame end.jpg \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/transition.mp4

# Subject reference (face consistency, ref mode uses S2V-01, 6s only)
bash scripts/video/generate_video.sh \
  --mode ref \
  --prompt "A young woman in a white dress walks slowly through a sunlit garden, [跟随] smooth tracking, warm natural lighting, cinematic depth of field" \
  --subject-image face.jpg \
  --duration 6 \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/person.mp4

Long-form Video (Multi-scene)

Multi-scene long videos chain segments together: the first segment generates via text-to-video (t2v), then each subsequent segment uses the last frame of the previous segment as its first frame (i2v). Segments are joined with crossfade transitions for smooth continuity. Default is 6 seconds per segment.

Workflow:

1. Segment 1: t2v — generated purely from the optimized text prompt
2. Segment 2+: i2v — the previous segment's last frame becomes first_frame_image, prompt describes motion and change from that ending state
3. All segments are concatenated with 0.5s crossfade transitions to eliminate jump cuts
4. Optional: AI-generated background music is overlaid

Prompt rules for each segment:

• Each segment prompt MUST be independently optimized using the Professional Formula
• Segment 1 (t2v): Full scene description with subject, scene, camera, atmosphere
• Segment 2+ (i2v): Focus on what changes and moves from the previous ending frame. Do NOT repeat the visual description — the first frame already provides it
• Maintain visual consistency: keep lighting, color grading, and style keywords consistent across segments
• Each segment covers only 6 seconds of action — keep it focused

# Example: 3-segment story with optimized per-segment prompts (default: 6s/segment, 768P)
bash scripts/video/generate_long_video.sh \
  --scenes \
    "A lone astronaut stands on a red desert planet surface, wind blowing dust particles, [推进] slow push in toward the visor, dramatic rim lighting, cinematic sci-fi atmosphere" \
    "The astronaut turns and begins walking toward a distant glowing structure on the horizon, dust swirling around boots, [跟随] tracking from behind, vast desolate landscape, golden light from the structure" \
    "The astronaut reaches the structure entrance, a massive doorway pulses with blue energy, [推进] slow push in toward the doorway, light reflects off the visor, awe-inspiring epic scale" \
  --music-prompt "cinematic orchestral ambient, slow build, sci-fi atmosphere" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/long_video.mp4

# With custom settings
bash scripts/video/generate_long_video.sh \
  --scenes "Scene 1 prompt" "Scene 2 prompt" \
  --segment-duration 6 \
  --resolution 768P \
  --crossfade 0.5 \
  --music-prompt "calm ambient background music" \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/long_video.mp4

Add Background Music

bash scripts/video/add_bgm.sh \
  --video input.mp4 \
  --generate-bgm --instrumental \
  --music-prompt "soft piano background" \
  --bgm-volume 0.3 \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/output_with_bgm.mp4

Template Video

bash scripts/video/generate_template_video.sh \
  --template-id 392753057216684038 \
  --media photo.jpg \
  --output ~/.openclaw/openclaw-data/multimodal/outputs/template_output.mp4

Video Models

Media Tools (Audio/Video Processing)

Entry point: scripts/media_tools.sh

Standalone FFmpeg-based utilities for format conversion, concatenation, extraction, trimming, and audio overlay. Use these when the user needs to process existing media files without generating new content via MiniMax API.

Video Format Conversion

# Convert between formats (mp4, mov, webm, mkv, avi, ts, flv)
bash scripts/media_tools.sh convert-video input.webm -o output.mp4
bash scripts/media_tools.sh convert-video input.mp4 -o output.mov

# With quality / resolution / fps options
bash scripts/media_tools.sh convert-video input.mp4 -o output.mp4 \
  --crf 18 --preset medium --resolution 1920x1080 --fps 30

Audio Format Conversion

# Convert between formats (mp3, wav, flac, ogg, aac, m4a, opus, wma)
bash scripts/media_tools.sh convert-audio input.wav -o output.mp3
bash scripts/media_tools.sh convert-audio input.mp3 -o output.flac \
  --bitrate 320k --sample-rate 48000 --channels 2

Video Concatenation

# Concatenate with crossfade transition (default 0.5s)
bash scripts/media_tools.sh concat-video seg1.mp4 seg2.mp4 seg3.mp4 -o merged.mp4

# Hard cut (no crossfade)
bash scripts/media_tools.sh concat-video seg1.mp4 seg2.mp4 -o merged.mp4 --crossfade 0

Audio Concatenation

# Simple concatenation
bash scripts/media_tools.sh concat-audio part1.mp3 part2.mp3 -o combined.mp3

# With crossfade
bash scripts/media_tools.sh concat-audio part1.mp3 part2.mp3 -o combined.mp3 --crossfade 1

Extract Audio from Video

# Extract as mp3
bash scripts/media_tools.sh extract-audio video.mp4 -o audio.mp3

# Extract as wav with higher bitrate
bash scripts/media_tools.sh extract-audio video.mp4 -o audio.wav --bitrate 320k

Video Trimming

# Trim by start/end time (seconds)
bash scripts/media_tools.sh trim-video input.mp4 -o clip.mp4 --start 5 --end 15

# Trim by start + duration
bash scripts/media_tools.sh trim-video input.mp4 -o clip.mp4 --start 10 --duration 8

Add Audio to Video (Overlay / Replace)

# Mix audio with existing video audio
bash scripts/media_tools.sh add-audio --video video.mp4 --audio bgm.mp3 -o output.mp4 \
  --volume 0.3 --fade-in 2 --fade-out 3

# Replace original audio entirely
bash scripts/media_tools.sh add-audio --video video.mp4 --audio narration.mp3 -o output.mp4 \
  --replace

Media File Info

bash scripts/media_tools.sh probe input.mp4

Script Architecture

scripts/
├── check_environment.sh         # Env verification (curl, ffmpeg, jq, xxd, API key)
├── media_tools.sh               # Audio/video conversion, concat, trim, extract
├── tts/
│   └── generate_voice.sh        # Unified TTS CLI (tts, clone, design, list-voices, generate, merge, convert)
├── music/
│   └── generate_music.sh        # Music generation CLI
├── image/
│   └── generate_image.sh        # Image generation CLI (2 modes: t2i, i2i)
└── video/
    ├── generate_video.sh        # Video generation CLI (4 modes: t2v, i2v, sef, ref)
    ├── generate_long_video.sh   # Multi-scene long video
    ├── generate_template_video.sh # Template-based video
    └── add_bgm.sh              # Background music overlay

References

Read these for detailed API parameters, voice catalogs, and prompt engineering:

• tts-guide.md — TTS setup, voice management, audio processing, segment format, troubleshooting
• tts-voice-catalog.md — Full voice catalog with IDs, descriptions, and parameter reference
• music-api.md — Music generation API: endpoints, parameters, response format
• image-api.md — Image generation API: text-to-image, image-to-image, parameters
• video-api.md — Video API: endpoints, models, parameters, camera instructions, templates
• video-prompt-guide.md — Video prompt engineering: formulas, styles, image-to-video tips