Merge pull request #239 from Qu-Ming-1/fix/mcp-v2-music-sunset

chore: retire Music CLI and SDK support

Author: AdrienDevv

ERRORS.md

@@ -125,20 +125,6 @@ All errors fall under [Network Errors](#networkerrors).
 
 ---
 
-## Music Commands
-
-### `mmx music generate`
-
-| Scenario | Error Message |
-|---|---|
-| Neither `--prompt` nor `--lyrics` provided | `At least one of --prompt or --lyrics is required.` |
-| `--lyrics-file` not found | `File not found: ${flags.lyricsFile}` |
-| `--lyrics-file` unreadable | `Cannot read file: ${e.message}` |
-| `--out` path no write permission | `Permission denied: cannot write to "${outPath}".` |
-| Disk full | `Disk full — cannot write audio file.` |
-
----
-
 ## Vision Commands
 
 ### `mmx vision describe`

README.md

@@ -1,8 +1,8 @@
-<img src="https://file.cdn.minimax.io/public/MMX.png" alt="MiniMax" width="100%" />
+<img src="https://file.cdn.minimax.io/public/MMX-capabilities.png" alt="MiniMax" width="100%" />
 
 <p align="center">
   <strong>The official CLI for the MiniMax AI Platform</strong><br>
-  Built for AI agents. Generate text, images, video, speech, and music — from any agent or terminal.
+  Built for AI agents. Generate text, images, video, and speech — from any agent or terminal.
 </p>
 
 <p align="center">
@@ -21,12 +21,11 @@
 - **Image** — Text-to-image with aspect ratio and batch controls
 - **Video** — Async video generation with progress tracking
 - **Speech** — TTS with 30+ voices, speed control, streaming playback
-- **Music** — Text-to-music with lyrics, instrumental mode, auto lyrics, and cover generation from reference audio
 - **Vision** — Image understanding and description
 - **Search** — Web search powered by MiniMax
 - **Dual Region** — Seamless Global (`api.minimax.io`) and CN (`api.minimaxi.com`) support
 
-<img src="https://file.cdn.minimax.io/public/MMX-CLI.png" alt="MiniMax" width="100%" />
+<img src="https://file.cdn.minimax.io/public/MMX-CLI-help.png" alt="MiniMax" width="100%" />
 
 ## Install
 
@@ -56,7 +55,6 @@ mmx text chat --message "What is MiniMax?"
 mmx image "A cat in a spacesuit"
 mmx speech synthesize --text "Hello!" --out hello.mp3
 mmx video generate --prompt "Ocean waves at sunset"
-mmx music generate --prompt "Upbeat pop" --lyrics "[verse] La da dee, sunny day"
 mmx search "MiniMax AI latest news"
 mmx vision photo.jpg
 mmx quota
@@ -113,20 +111,6 @@ echo "Breaking news" | mmx speech synthesize --text-file - --out news.mp3
 mmx speech voices
 ```
 
-### `mmx music`
-
-```bash
-# Generate with lyrics
-mmx music generate --prompt "Upbeat pop" --lyrics "[verse] La da dee, sunny day" --out song.mp3
-# Auto-generate lyrics from prompt
-mmx music generate --prompt "Indie folk, melancholic, rainy night" --lyrics-optimizer --out song.mp3
-# Instrumental (no vocals)
-mmx music generate --prompt "Cinematic orchestral" --instrumental --out bgm.mp3
-# Cover — generate a cover version from a reference audio file
-mmx music cover --prompt "Jazz, piano, warm female vocal" --audio-file original.mp3 --out cover.mp3
-mmx music cover --prompt "Indie folk" --audio https://example.com/song.mp3 --out cover.mp3
-```
-
 ### `mmx vision`
 
 ```bash

README_CN.md

@@ -1,8 +1,8 @@
-<img src="https://file.cdn.minimax.io/public/MMX.png" alt="MiniMax" width="100%" />
+<img src="https://file.cdn.minimax.io/public/MMX-capabilities.png" alt="MiniMax" width="100%" />
 
 <p align="center">
   <strong>MiniMax AI 开放平台官方命令行工具</strong><br>
-  专为 AI Agent 打造。在任意 Agent 或终端中生成文字、图像、视频、语音和音乐。
+  专为 AI Agent 打造。在任意 Agent 或终端中生成文字、图像、视频和语音。
 </p>
 
 <p align="center">
@@ -21,12 +21,11 @@
 - **图像生成** — 文生图，支持比例和批量控制
 - **视频生成** — 异步生成，进度追踪
 - **语音合成** — 30+ 音色、语速调节、流式播放
-- **音乐生成** — 文生音乐，支持自定义歌词、纯音乐、自动生词，以及基于参考音频的 Cover 生成
 - **图像理解** — 图片描述与识别
 - **网络搜索** — MiniMax 搜索引擎
 - **双区域** — 国际版（`api.minimax.io`）和国内版（`api.minimaxi.com`）自动切换
 
-<img src="https://file.cdn.minimax.io/public/MMX-CLI.png" alt="MiniMax" width="100%" />
+<img src="https://file.cdn.minimax.io/public/MMX-CLI-help.png" alt="MiniMax" width="100%" />
 
 ## 安装
 
@@ -56,7 +55,6 @@ mmx text chat --message "你好，MiniMax！"
 mmx image "一只穿宇航服的猫"
 mmx speech synthesize --text "你好！" --out hello.mp3
 mmx video generate --prompt "海浪拍打礁石"
-mmx music generate --prompt "欢快的流行乐" --lyrics "[主歌] 啦啦啦，阳光照"
 mmx search "MiniMax AI 最新动态"
 mmx vision photo.jpg
 mmx quota
@@ -113,20 +111,6 @@ echo "头条新闻" | mmx speech synthesize --text-file - --out news.mp3
 mmx speech voices
 ```
 
-### `mmx music`
-
-```bash
-# 带歌词生成
-mmx music generate --prompt "欢快的流行乐" --lyrics "[主歌] 啦啦啦，阳光照" --out song.mp3
-# 自动生成歌词
-mmx music generate --prompt "忧郁的独立民谣，雨夜" --lyrics-optimizer --out song.mp3
-# 纯音乐（无人声）
-mmx music generate --prompt "史诗管弦乐" --instrumental --out bgm.mp3
-# Cover — 基于参考音频生成翻唱版本
-mmx music cover --prompt "爵士钢琴，慵懒女声" --audio-file original.mp3 --out cover.mp3
-mmx music cover --prompt "民谣吉他" --audio https://example.com/song.mp3 --out cover.mp3
-```
-
 ### `mmx vision`
 
 ```bash

SDK.md

@@ -122,67 +122,6 @@ const voices = await sdk.speech.voices();
 const englishVoices = await sdk.speech.voices('en');
 ```
 
-### Music
-
-```typescript
-const music = await sdk.music.generate({
-  model: 'music-3.0',
-  prompt: 'Upbeat pop song',
-  lyrics: '[verse] La da dee, sunny day',
-  output_format: 'hex',
-});
-
-// Instrumental
-const instrumental = await sdk.music.generate({
-  prompt: 'Cinematic orchestral',
-  is_instrumental: true,
-});
-
-// Auto-generate lyrics
-const autoLyrics = await sdk.music.generate({
-  prompt: 'Indie folk, melancholic, rainy night',
-  lyrics_optimizer: true,
-});
-
-// Streaming
-const stream = await sdk.music.generate({
-  prompt: 'Upbeat pop',
-  lyrics: '[verse] Hello world',
-  stream: true,
-});
-
-for await (const chunk of stream) {
-  // chunk contains decoded audio bytes
-}
-
-// One-step cover — lyrics are extracted from the reference audio when omitted
-const cover = await sdk.music.generate({
-  model: 'music-cover-free',
-  prompt: 'Jazz piano trio with a warm intimate vocal',
-  audio_url: 'https://example.com/reference.mp3',
-  output_format: 'url',
-});
-
-// Two-step cover — use a feature ID returned by the cover preprocess API
-const rewrittenCover = await sdk.music.generate({
-  model: 'music-cover',
-  prompt: 'Acoustic folk with gentle strings and soft vocals',
-  cover_feature_id: 'feature-id-from-preprocess',
-  lyrics: '[Verse]\nThese are the rewritten lyrics for the cover',
-});
-
-// Structured prompt
-const structured = await sdk.music.generate({
-  prompt: 'A beautiful song',
-  vocals: 'warm male baritone',
-  genre: 'jazz',
-  mood: 'relaxing',
-  instruments: 'piano, saxophone',
-  bpm: 120,
-  key: 'C major',
-});
-```
-
 ### Vision
 
 ```typescript

docs/cli-design.md

@@ -28,8 +28,6 @@ mmx
 │   ├── task
 │   │   └── get            Query video task status
 │   └── download           Download a completed video by file ID
-├── music
-│   └── generate           Generate a song (music-3.0)
 ├── quota
 │   └── show               Display Token Plan usage and remaining quotas
 └── config

package-lock.json

@@ -1,6 +1,6 @@
 {
   "name": "mmx-cli",
-  "version": "1.0.19",
+  "version": "1.0.20",
   "description": "CLI for the MiniMax AI Platform",
   "type": "module",
   "repository": {

package.json

@@ -1,11 +1,11 @@
 ---
 name: mmx-cli
-description: 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 models, perform web search, or manage MiniMax API resources from the terminal.
+description: Use mmx to generate text, images, video, and speech via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal.
 ---
 
 # MiniMax CLI — Agent Skill Guide
 
-Use `mmx` to generate text, images, video, speech, music, and perform web search via the MiniMax AI platform.
+Use `mmx` to generate text, images, video, speech, and perform web search via the MiniMax AI platform.
 
 ## Prerequisites
 
@@ -205,105 +205,6 @@ echo "Breaking news." | mmx speech synthesize --text-file - --out news.mp3
 
 ---
 
-### music generate
-
-Generate music. Responds well to rich, structured descriptions.
-
-**Model:** `music-3.0` — default model.
-
-```bash
-mmx music generate --prompt <text> [--lyrics <text>] [flags]
-```
-
-| Flag | Type | Description |
-|---|---|---|
-| `--prompt <text>` | string | Music style description (can be detailed) |
-| `--lyrics <text>` | string | Song lyrics with structure tags. Required unless `--instrumental` or `--lyrics-optimizer` is used. |
-| `--lyrics-file <path>` | string | Read lyrics from file. Use `-` for stdin |
-| `--lyrics-optimizer` | boolean | Auto-generate lyrics from prompt. Cannot be used with `--lyrics` or `--instrumental`. |
-| `--instrumental` | boolean | Generate instrumental music (no vocals). Cannot be used with `--lyrics`. |
-| `--vocals <text>` | string | Vocal style, e.g. `"warm male baritone"`, `"bright female soprano"`, `"duet with harmonies"` |
-| `--genre <text>` | string | Music genre, e.g. folk, pop, jazz |
-| `--mood <text>` | string | Mood or emotion, e.g. warm, melancholic, uplifting |
-| `--instruments <text>` | string | Instruments to feature, e.g. `"acoustic guitar, piano"` |
-| `--tempo <text>` | string | Tempo description, e.g. fast, slow, moderate |
-| `--bpm <number>` | number | Exact tempo in beats per minute |
-| `--key <text>` | string | Musical key, e.g. C major, A minor, G sharp |
-| `--avoid <text>` | string | Elements to avoid in the generated music |
-| `--use-case <text>` | string | Use case context, e.g. `"background music for video"`, `"theme song"` |
-| `--structure <text>` | string | Song structure, e.g. `"verse-chorus-verse-bridge-chorus"` |
-| `--references <text>` | string | Reference tracks or artists, e.g. `"similar to Ed Sheeran"` |
-| `--extra <text>` | string | Additional fine-grained requirements |
-| `--aigc-watermark` | boolean | Embed AI-generated content watermark |
-| `--format <fmt>` | string | Audio format (default: `mp3`) |
-| `--sample-rate <hz>` | number | Sample rate (default: 44100) |
-| `--bitrate <bps>` | number | Bitrate (default: 256000) |
-| `--out <path>` | string | Save audio to file |
-| `--stream` | boolean | Stream raw audio to stdout |
-
-At least one of `--prompt` or `--lyrics` is required.
-
-```bash
-# With lyrics
-mmx music generate --prompt "Upbeat pop" --lyrics "La la la..." --out song.mp3 --quiet
-
-# Auto-generate lyrics from prompt
-mmx music generate --prompt "Upbeat pop about summer" --lyrics-optimizer --out summer.mp3 --quiet
-
-# Instrumental
-mmx music generate --prompt "Cinematic orchestral, building tension" --instrumental --out bgm.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
-```
-
----
-
-### music cover
-
-Generate a cover version of a song based on reference audio.
-
-**Model:** `music-cover-free` — unlimited for API key users, RPM = 3.
-
-```bash
-mmx music cover --prompt <text> (--audio <url> | --audio-file <path>) [flags]
-```
-
-| Flag | Type | Description |
-|---|---|---|
-| `--prompt <text>` | string, **required** | Target cover style, e.g. `"Indie folk, acoustic guitar, warm male vocal"` |
-| `--audio <url>` | string | URL of reference audio (mp3, wav, flac, etc. — 6s to 6min, max 50MB) |
-| `--audio-file <path>` | string | Local reference audio file (auto base64-encoded) |
-| `--lyrics <text>` | string | Cover lyrics. If omitted, extracted from reference audio via ASR. |
-| `--lyrics-file <path>` | string | Read lyrics from file. Use `-` for stdin |
-| `--seed <number>` | number | Random seed 0–1000000 for reproducible results |
-| `--format <fmt>` | string | Audio format: `mp3`, `wav`, `pcm` (default: `mp3`) |
-| `--sample-rate <hz>` | number | Sample rate (default: 44100) |
-| `--bitrate <bps>` | number | Bitrate (default: 256000) |
-| `--channel <n>` | number | Channels: `1` (mono) or `2` (stereo, default) |
-| `--out <path>` | string | Save audio to file |
-| `--stream` | boolean | Stream raw audio to stdout |
-
-```bash
-# Cover from URL
-mmx music cover --prompt "Indie folk, acoustic guitar, warm male vocal" \
-  --audio https://filecdn.minimax.chat/public/d20eda57-2e36-45bf-9e12-82d9f2e69a86.mp3 --out cover.mp3 --quiet
-
-# Cover from local file with custom lyrics
-mmx music cover --prompt "Jazz, piano, slow" \
-  --audio-file original.mp3 --lyrics-file lyrics.txt --out jazz_cover.mp3 --quiet
-
-# Reproducible result with seed
-mmx music cover --prompt "Pop, upbeat" --audio https://filecdn.minimax.chat/public/d20eda57-2e36-45bf-9e12-82d9f2e69a86.mp3 --seed 42 --out cover.mp3
-```
-
----
-
 ### vision describe
 
 Image understanding via VLM. Provide either `--image` or `--file-id`, not both.
@@ -428,13 +329,11 @@ Set per-modality defaults so you don't need `--model` every time:
 mmx config set --key default-text-model --value MiniMax-M3
 mmx config set --key default-speech-model --value speech-2.8-hd
 mmx config set --key default-video-model --value MiniMax-Hailuo-2.3
-mmx config set --key default-music-model --value music-3.0
 
 # Use without --model
 mmx text chat --message "Hello"
 mmx speech synthesize --text "Hello" --out hello.mp3
 mmx video generate --prompt "Ocean waves"
-mmx music generate --prompt "Upbeat pop" --instrumental
 
 # --model still overrides per-call
 mmx text chat --model MiniMax-M3 --message "Hello"

skill/SKILL.md

@@ -34,14 +34,6 @@ export function fileRetrieveEndpoint(baseUrl: string, fileId: string): string {
   return `${baseUrl}/v1/files/retrieve?file_id=${fileId}`;
 }
 
-export function musicEndpoint(baseUrl: string): string {
-  return `${baseUrl}/v1/music_generation`;
-}
-
-export function musicCoverPreprocessEndpoint(baseUrl: string): string {
-  return `${baseUrl}/v1/music_cover_preprocess`;
-}
-
 export function searchEndpoint(baseUrl: string): string {
   return `${baseUrl}/v1/coding_plan/search`;
 }