Skip to main content
This guide explains how to integrate deAPI with n8n to automate AI-powered workflows such as image generation, video transcription, and more.

​
What is n8n?

n8n is an open-source workflow automation tool that allows you to connect different services and APIs together. With deAPI’s HTTP API, you can build powerful automation workflows that generate images, transcribe videos, create speech, and more — all without writing code.

​
Prerequisites

Before you begin, ensure you have:
  • An n8n instance (self-hosted or n8n Cloud)
  • A deAPI API key from the deAPI Dashboard
  • Basic understanding of n8n workflows

​
Authentication Setup

All deAPI endpoints require Bearer token authentication. In n8n, configure this once and reuse it across your workflow:
  1. In your HTTP Request node, set Authentication to Generic Credential Type
  2. Set Generic Auth Type to Bearer Auth
  3. Create a new credential with your deAPI API key as the token

​
Example Workflow: Text-to-Image Generation

This example demonstrates a complete workflow that generates an image from a text prompt using deAPI’s asynchronous job model.

​
Workflow Overview

The workflow follows deAPI’s queued execution model:
  1. Submit job — POST request to start image generation
  2. Poll status — Check job status in a loop
  3. Check completion — Verify if result_url exists
  4. Download result — Fetch the generated image
+---------------------+
|   Manual Trigger    |
+----------+----------+
           |
           v
+---------------------+
|    HTTP Request     |  POST /api/v1/client/txt2img
|    (Submit Job)     |
+----------+----------+
           |
           v
+---------------------+
|   HTTP Request1     |<-----------+
|   (Check Status)    |            |
+----------+----------+            |
           |                       |
           v                       |
+---------------------+            |
|         If          |            |
| (result_url exists) |            |
+----------+----------+            |
           |                       |
     +-----+-----+                 |
     |           |                 |
   True        False               |
     |           |                 |
     v           v                 |
+----------+ +----------+          |
|   HTTP   | |   Wait   |----------+
| Request2 | | (3 sec)  |
|(Download)| +----------+
+----------+

​
Step 1: Trigger Node

Add a Manual Trigger (or any trigger like Webhook, Schedule) to start the workflow.

​
Step 2: Submit Generation Request (HTTP Request)

Add an HTTP Request node with the following configuration:
SettingValue
MethodPOST
URLhttps://api.deapi.ai/api/v1/client/txt2img
AuthenticationGeneric Credential Type
Generic Auth TypeBearer Auth
Bearer AuthSelect your deAPI credential
Send BodyEnabled (toggle ON)
Body Content TypeJSON
Specify BodyUsing JSON
JSON Body: 
{
  "seed": 1312321313,
  "loras": [],
  "model": "ZImageTurbo_INT8",
  "steps": 8,
  "width": 1024,
  "height": 1024,
  "prompt": "Red Bull F1 car from 2025",
  "guidance": 3.5,
  "negative_prompt": null
}
The response will contain a request_id: 
{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}

​
Step 3: Poll Job Status (HTTP Request1)

Add a second HTTP Request node to check the job status:
SettingValue
MethodGET
URLhttps://api.deapi.ai/api/v1/client/request-status/{{ $node["HTTP Request"].json.data.request_id }}
AuthenticationGeneric Credential Type
Generic Auth TypeBearer Auth
Bearer AuthSelect your deAPI credential
The URL uses n8n expression syntax to reference the request_id from the previous node.
The response includes job status: 
{
  "data": {
    "status": "done",
    "progress": 100,
    "result_url": "https://depinprod.s3.pl-waw.scw.cloud/depin-result/..."
  }
}

​
Step 4: Check if Result is Ready (If Node)

Add an If node to check whether the job has completed.
The following condition:
SettingValue
Value 1{{ $json.data.result_url }}
Operationexists
Connect the outputs:
  • True → HTTP Request2 (download result)
  • False → Wait node (retry loop)

​
Step 5: Wait Before Retry (Wait Node)

Add a Wait node for the False branch:
SettingValue
ResumeAfter Time Interval
Wait Amount3
Wait UnitSeconds
Connect the Wait node output back to HTTP Request1 to create the polling loop.

​
Step 6: Download Result (HTTP Request2)

Add a final HTTP Request node for the True branch:
SettingValue
MethodGET
URL{{ $json.data.result_url }}
AuthenticationNone
Options → Response → Response FormatFile
Options → Response → Put Output in Fielddata
The generated image is now available in your workflow for further processing (save to disk, upload to cloud storage, send via email, etc.).

​
Tips & Best Practices

​
Polling Interval

Adjust the Wait node timing based on task type:
Task TypeRecommended Wait
Text-to-Image2–5 seconds
Image-to-Image10–15 seconds
Text-to-Video5–10 seconds
Video Transcription5–15 seconds
Audio Transcription3–10 seconds

​
Error Handling

Add error handling to your workflow:
  • Check for status: "error" in the polling response
  • Set a maximum number of loop iterations to avoid infinite loops (use a counter with Set node)
  • Use n8n’s built-in Error Trigger node for workflow-level error handling

​
Reusable Credentials

Create a single Bearer Auth credential named “deAPI” and reuse it across all HTTP Request nodes.

​
Other Endpoints

Use the same polling pattern for all deAPI endpoints:
ServicePOST Endpoint
Text-to-Image/api/v1/client/txt2img
Image-to-Image/api/v1/client/img2img
Text-to-Video/api/v1/client/txt2video
Image-to-Video/api/v1/client/img2video
Text-to-Speech/api/v1/client/txt2audio
Video-to-Text (URL)/api/v1/client/vid2txt
Video-to-Text (File)/api/v1/client/videofile2txt
Audio-to-Text (File)/api/v1/client/audiofile2txt
Audio-to-Text (X Spaces)/api/v1/client/aud2txt
Background Removal/api/v1/client/img-rmbg
OCR (Image-to-Text)/api/v1/client/img2txt
Text-to-Embedding/api/v1/client/txt2embedding
All endpoints follow the same pattern:
  1. POST to submit the job → receive request_id
  2. GET /api/v1/client/request-status/{request_id} → poll status
  3. When status: "done" → use result_url or result

​
Resources