Download Task Result - Memories.ai API Tools

Product: Visual Agents Use case: Managed endpoints powering Memories.ai’s open-source video search and editing agents (queries, video clipping/editing, screenplay extraction) Host: https://mavi-backend.memories.ai/serve/api/v2 Auth: Authorization: sk-mavi-... (no Bearer prefix)

This endpoint downloads all output files from a completed screenplay extraction task as a single zip archive. The zip contains storyboard files, transcript JSONs, namelist, and/or merged XLSX based on the configuration used when submitting the task.

Pricing:

$0.12/1GB download (based on total original file sizes, not compressed zip size)

Response Behavior:

✅ Success: Returns zip file stream (binary data) — browser automatically downloads to local storage
❌ Error: Returns JSON error — use json() to parse error message

Key Points:

Success response is a file (binary data), NOT JSON
The zip filename is {task_id}.zip
Error response is JSON with error details
Task must be in completed status, otherwise an error is returned
Check response status before deciding how to handle the response

Code Examples

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";
const fs = require('fs');

const taskId = "ros-sd-20260313-a3f8c2b1";
const response = await fetch(`${BASE_URL}/screenplay/tasks/${taskId}/download`, {
  method: 'GET',
  headers: {
    'Authorization': API_KEY
  }
});

if (response.ok) {
  // Success: save as zip file
  const buffer = await response.arrayBuffer();
  fs.writeFileSync(`${taskId}.zip`, Buffer.from(buffer));
  console.log(`Downloaded ${taskId}.zip`);
} else {
  // Error: parse JSON
  const error = await response.json();
  console.error('Download failed:', error);
}

import axios from 'axios';
import fs from 'fs';

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";

const taskId = "ros-sd-20260313-a3f8c2b1";
try {
  const response = await axios.get(`${BASE_URL}/screenplay/tasks/${taskId}/download`, {
    headers: {
      'Authorization': API_KEY
    },
    responseType: 'arraybuffer'
  });

  fs.writeFileSync(`${taskId}.zip`, response.data);
  console.log(`Downloaded ${taskId}.zip`);
} catch (error) {
  console.error('Download failed:', error.response?.data);
}

import requests

BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2"
API_KEY = "sk-mavi-..."
HEADERS = {
    "Authorization": f"{API_KEY}"
}

def download_screenplay_result(task_id):
    url = f"{BASE_URL}/screenplay/tasks/{task_id}/download"
    response = requests.get(url, headers=HEADERS, stream=True)

    if response.status_code == 200:
        filename = f"{task_id}.zip"
        with open(filename, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)
        print(f"Downloaded {filename}")
    else:
        print(f"Download failed: {response.json()}")

# Usage example
download_screenplay_result("ros-sd-20260313-a3f8c2b1")

Path Parameters

Parameter	Type	Required	Description
task_id	string	Yes	The screenplay task ID of a completed task

Response

On success, returns a binary zip file stream with the following headers:

Header	Value
Content-Type	`application/zip`
Content-Disposition	`attachment; filename="{task_id}.zip"`

Zip File Contents

The zip archive contains the following files based on your task configuration:

Config Flag	Files Included	Description
`require_json: true`	`_transcript.json`, `_storyboard.json`, `namelist.json`	Per-episode transcript and storyboard JSONs, plus a global character namelist
`require_xlsx: true`	`*.xlsx` (per episode)	Per-episode storyboard spreadsheets
`require_merge_xlsx: true`	`merged.xlsx`	Single merged spreadsheet combining all episodes

Error Responses

Scenario	Error Message
Task not found	`"Task not found for id: {task_id}"`
Task not completed	`"Task is not completed yet, current status: {status}"`
No result data	`"No result data available for this task."`
No files found	`"No downloadable files found for this task."`
Insufficient balance	`"Insufficient balance to download the resource. Please recharge and try again."`

Notes

The task must be in completed status — check with Get Task Status first
Download cost is calculated based on the sum of all individual file sizes (original sizes, not compressed)
Files with duplicate names are automatically renamed with a numeric suffix (e.g., file.json, file_1.json)
The zip is streamed directly — no intermediate storage is used

​Code Examples

​Path Parameters

​Response

​Zip File Contents

​Error Responses

​Notes

Code Examples

Path Parameters

Response

Zip File Contents

Error Responses

Notes