agent-media

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Media

Agent Media is an agent-first media toolkit that provides CLI-accessible commands for image, video, and audio processing. All commands produce deterministic, machine-readable JSON output.

Agent Media是一款面向Agent的媒体工具包，提供可通过CLI调用的图片、视频和音频处理命令。所有命令均输出确定性、机器可读的JSON格式结果。

Available Commands

可用命令

Image Commands

图片命令

```
agent-media image resize
```
- Resize an image
```
agent-media image convert
```
- Convert image format
```
agent-media image remove-background
```
- Remove image background
```
agent-media image generate
```
- Generate image from text

```
agent-media image resize
```
- 调整图片尺寸
```
agent-media image convert
```
- 转换图片格式
```
agent-media image remove-background
```
- 移除图片背景
```
agent-media image generate
```
- 基于文本生成图片

Audio Commands

音频命令

```
agent-media audio extract
```
- Extract audio from video
```
agent-media audio transcribe
```
- Transcribe audio to text

```
agent-media audio extract
```
- 从视频中提取音频
```
agent-media audio transcribe
```
- 将音频转写为文本

Video Commands

视频命令

```
agent-media video generate
```
- Generate video from text or image

```
agent-media video generate
```
- 基于文本或图片生成视频

Output Format

输出格式

All commands return JSON to stdout:

json

{
  "ok": true,
  "media_type": "image",
  "action": "resize",
  "provider": "local",
  "output_path": "output_123.webp",
  "mime": "image/webp",
  "bytes": 12345
}

On error:

json

{
  "ok": false,
  "error": {
    "code": "INVALID_INPUT",
    "message": "input file not found"
  }
}

所有命令均向标准输出（stdout）返回JSON：

json

{
  "ok": true,
  "media_type": "image",
  "action": "resize",
  "provider": "local",
  "output_path": "output_123.webp",
  "mime": "image/webp",
  "bytes": 12345
}

错误时返回：

json

{
  "ok": false,
  "error": {
    "code": "INVALID_INPUT",
    "message": "input file not found"
  }
}

Providers

服务提供商

local - Default provider using Sharp (resize, convert) and Transformers.js (remove-background, transcribe)
fal - fal.ai provider (generate, edit, remove-background, transcribe, video)
replicate - Replicate API (generate, edit, remove-background, transcribe, video)
runpod - Runpod API (generate, edit)
ai-gateway - Vercel AI Gateway (generate, edit)

local - 默认提供商，使用Sharp（调整尺寸、格式转换）和Transformers.js（移除背景、语音转写）
fal - fal.ai提供商（生成、编辑、移除背景、语音转写、视频处理）
replicate - Replicate API（生成、编辑、移除背景、语音转写、视频处理）
runpod - Runpod API（生成、编辑）
ai-gateway - Vercel AI Gateway（生成、编辑）

Provider Selection

提供商选择

Explicit:
```
--provider <name>
```
Auto-detect from environment variables
Fallback to local provider

显式指定：
```
--provider <name>
```
通过环境变量自动检测
回退至local提供商

Environment Variables

环境变量

```
AGENT_MEDIA_DIR
```
- Custom output directory
```
FAL_API_KEY
```
- Enable fal provider
```
REPLICATE_API_TOKEN
```
- Enable replicate provider
```
RUNPOD_API_KEY
```
- Enable runpod provider
```
AI_GATEWAY_API_KEY
```
- Enable ai-gateway provider

```
AGENT_MEDIA_DIR
```
- 自定义输出目录
```
FAL_API_KEY
```
- 启用fal提供商
```
REPLICATE_API_TOKEN
```
- 启用replicate提供商
```
RUNPOD_API_KEY
```
- 启用runpod提供商
```
AI_GATEWAY_API_KEY
```
- 启用ai-gateway提供商