脚本编写器

关于此流水线的文章

• 什么是生成式 AI：工作原理与它能创造什么

• 如何制作 AI 视频：从提示词到成片

脚本编写器 API

从你自己的代码调用此流水线。一次请求即可发起运行；模型是一个输入字段，而不是独立的接口。

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "script-writer",
  input: {
    topic: "why sourdough starters actually work",
    genre: "documentary",
  },
});

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="script-writer",
    input={
        "topic": "why sourdough starters actually work",
        "genre": "documentary",
    },
))

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "topic": "why sourdough starters actually work",
  "genre": "documentary"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "script-writer", input)
if err != nil {
    log.Fatal(err)
}

pipe2 pipelines run \
  --pipeline script-writer \
  --input-json '{"topic": "why sourdough starters actually work", "genre": "documentary"}' \
  --wait

获取 API 令牌 →

参数

genre 必填

Tone and format of the script — drives pacing, structure and voice.

documentaryeducationalexplainerpromocinematic 默认 documentary

topic 必填

你的视频讲的是什么？

string

duration_min

Target read time in minutes. The script is written to fit.

13510 默认 1

在 AI 智能体中使用

将任意 MCP 客户端指向 pipe2，你的智能体就能获得这些工具。它会找到这条流水线，读取上方相同的 schema，然后运行它。

• list_pipelines
• get_pipeline_schema
• run_pipeline
• get_pipeline_run_status
• request_upload

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

完整 API 参考→ MCP 设置→ CLI 参考→

常见问题