>_ Bailian CLI

The official command-line interface for Alibaba Cloud Bailian (DashScope) AI Platform

中文文档 · API Documentation · Get API Key

Chat with Qwen, generate images & videos, understand images, call agents, manage memory, search the web — all from your terminal.

Built for AI Agents. Every command works as a structured tool call.

Installation

npm install -g bailian-cli

After installation, both bailian and bl (short alias) are available.

Quick Start

# Authenticate
bl auth login --api-key sk-xxxxx

# Chat with Qwen
bl text chat --message "What is DashScope?"

# Multimodal chat (text + image + audio + video)
bl omni --message "Describe this image" --image ./photo.jpg

# Generate an image
bl image generate --prompt "A cat in a spacesuit" --out-dir ./images/

# Generate a video from local image
bl video generate --image ./cat.png --prompt "Make the cat move" --download cat.mp4

Features

Local File Support: All commands accepting file URLs also accept local file paths — files are auto-uploaded. Just pass ./photo.png instead of a URL.

| Category | Commands | Default Model | |:---------|:---------|:--------------| | Text | text chat | qwen3.6-plus | | Omni | omni (text+image+audio+video) | qwen3.5-omni-plus | | Image | image generate | qwen-image-2.0 | | | image edit (multi-image merge) | qwen-image-2.0 | | Video | video generate (text/image-to-video) | happyhorse-1.0-t2v / happyhorse-1.0-i2v | | | video edit (style transfer) | happyhorse-1.0-video-edit | | | video task get / video download | — |

| Category | Commands | Default Model | |:---------|:---------|:--------------| | Vision | vision describe | qwen-vl-max | | Speech | speech synthesize (TTS) | cosyvoice-v3-flash | | | speech recognize (ASR) | fun-asr | | File | file upload (to temp OSS) | — | | App | app call (agents / workflows) | — | | Memory | memory add/search/list/update/delete | — | | Knowledge | knowledge retrieve (RAG) | — | | Search | search web | — |

Usage Examples

Text Chat

# Simple chat
bl text chat --message "Explain quantum computing"

# Multi-turn conversation
bl text chat --message "Hello" --message "assistant:Hi!" --message "How are you?"

# With system prompt
bl text chat --system "You are a coding assistant." --message "Write fizzbuzz in Python"

# Enable thinking mode (qwen3 / qwq)
bl text chat --model qwq-plus --message "Solve 1+1" --enable-thinking

Omni Multimodal

# Describe an image
bl omni --message "What's in this photo?" --image ./photo.jpg

# Understand audio
bl omni --message "Transcribe this audio" --audio ./recording.wav

# Generate speech output
bl omni --message "Read this aloud" --audio-out greeting.wav

Image Generation & Editing

# Generate images
bl image generate --prompt "Mountain landscape" --size 16:9

# Generate multiple images
bl image generate --prompt "Logo design" --n 3 --out-dir ./generated/

# Edit an image (local file auto-uploaded)
bl image edit --image ./photo.png --prompt "Change background to beach"

# Multi-image merge
bl image edit --image ./a.png --image ./b.png --prompt "Combine into a collage"

Video Generation & Editing

# Text to video
bl video generate --prompt "A person reading a book" --download output.mp4

# Image to video (local file auto-uploaded)
bl video generate --image ./cat.png --prompt "Make the cat move" --ratio 3:4

# Edit a video (style transfer)
bl video edit --video ./input.mp4 --prompt "Convert to clay style"

Speech

# List available voices
bl speech synthesize --list-voices --model cosyvoice-v3-flash

# Text-to-speech
bl speech synthesize --text "Hello world" --voice longyumi_v3 --out speech.wav

# Stream to audio player (macOS)
bl speech synthesize --text "你好" --voice longyumi_v3 --stream | afplay -

# Speech-to-text (local file auto-uploaded)
bl speech recognize --url ./meeting.mp3

File Upload, App, Memory & Knowledge

# Upload a local file to DashScope temp storage
bl file upload --file ./photo.png --model qwen-vl-max

# Call a Bailian application
bl app call --app-id <APP_ID> --prompt "Hello" --stream

# Memory management
bl memory add --user-id user1 --content "User prefers Python"
bl memory search --user-id user1 --query "programming language"

# Knowledge base retrieval (requires AK/SK)
bl knowledge retrieve --index-id <INDEX_ID> --query "search text"

# Web search
bl search web --query "latest TypeScript features" --count 5

Authentication

DashScope API Key

Required for most commands. Get your key from the DashScope Console.

# Option 1: Environment variable
export DASHSCOPE_API_KEY=sk-xxxxx

# Option 2: Login command (persisted to ~/.bailian/config.json)
bl auth login --api-key sk-xxxxx

# Option 3: Per-command flag
bl text chat --api-key sk-xxxxx --message "Hello"

Alibaba Cloud AK/SK (Knowledge Base only)

Required for knowledge retrieve. Get your AccessKey from RAM Console.

export ALIBABA_CLOUD_ACCESS_KEY_ID=LTAI5t...
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=...
export BAILIAN_WORKSPACE_ID=ws-...

Configuration

# View current config
bl config show

# Set defaults
bl config set --key region --value us
bl config set --key default_text_model --value qwen-turbo
bl config set --key timeout --value 600

# Export MCP-compatible JSON Schema for all commands
bl config export-schema

# Self-update to latest version
bl update

Config file location: ~/.bailian/config.json

Global Flags

| Flag | Description | |:-----|:------------| | --api-key <key> | API key (overrides all other auth) | | --region <region> | API region: cn (default), us, intl | | --output <format> | Output format: text, json | | --quiet | Suppress non-essential output | | --verbose | Print HTTP request/response details | | --dry-run | Show what would happen without executing | | --no-color | Disable ANSI colors and spinners | | --timeout <seconds> | Request timeout (default: 300) | | --non-interactive | Disable interactive prompts (CI mode) |

Project Structure

src/
├── main.ts              # CLI entry point
├── registry.ts          # Command registry (30 commands)
├── args.ts              # Argument parsing
├── command.ts           # Command interface & global options
├── auth/                # Authentication (credentials, resolver, setup)
├── client/              # HTTP client (AK signing, endpoints, streaming)
├── commands/            # Command implementations
│   ├── auth/            #   login, status, logout
│   ├── text/            #   chat
│   ├── omni/            #   multimodal chat
│   ├── image/           #   generate, edit
│   ├── video/           #   generate, edit, task-get, download
│   ├── vision/          #   describe
│   ├── speech/          #   synthesize, recognize
│   ├── file/            #   upload
│   ├── app/             #   call
│   ├── memory/          #   add, search, list, update, delete, profile
│   ├── knowledge/       #   retrieve
│   ├── search/          #   web
│   └── config/          #   show, set, export-schema
├── config/              # Config loading & schema (Zod)
├── errors/              # Error handling hierarchy
├── output/              # Formatters (text, json, progress, status-bar)
├── polling/             # Async task polling
├── update/              # Self-update checker
└── utils/               # Utilities (fs, token, env, prompt)

Links

| Resource | URL | |:---------|:----| | DashScope API Docs | https://help.aliyun.com/zh/model-studio/ | | Qwen Model List | https://help.aliyun.com/zh/model-studio/getting-started/models | | Bailian Console | https://bailian.console.aliyun.com/ | | Get API Key | https://bailian.console.aliyun.com/cn-beijing/?source_channel=aliway&tab=app#/api-key | | Get AccessKey | https://ram.console.aliyun.com/manage/ak |

Made with >_ by the Bailian team