OpenAI examples: ChatGPT, DALLE-2, Whisper-1 – 5-in-1
Needs changesNeeds changes. This template uses 2 thing(s) that n8n 3.0 removes: OpenAI (legacy), Read Binary Files. 2 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This workflow has 17 nodes and runs manually, when you click “Execute workflow”. It uses only n8n's built-in nodes. It also calls api.openai.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- LoadMP (Read Binary Files): uses Read Binary Files
- Set-ex (Edit Fields (Set)): sets or maps fields
- ChatGPT-ex (OpenAI): work with chat
- Whisper-transcribe (HTTP Request): calls api.openai.com (POST)
- ChatGPT-ex (OpenAI): work with chat
- Text-example (Code): runs custom JavaScript code
- HTML: parses or builds HTML
- davinci-003-complete (OpenAI): uses OpenAI
- ChatGPT-ex1. (OpenAI): work with chat
- ChatGPT-ex (OpenAI): work with chat
…plus 6 more steps. See the full node list below.
HTTP calls to: api.openai.com
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- OpenAI (legacy) in davinci-003-complete, ChatGPT-ex2, davinci-003-edit…: replace with OpenAI node (AI section).
- Read Binary Files in LoadMP3: replace with Read/Write Files from Disk.
| Removed in 3.0 | Replace with |
|---|---|
| OpenAI (legacy) davinci-003-complete, ChatGPT-ex2, davinci-003-edit, ChatGPT-ex1.1, ChatGPT-ex1.2, ChatGPT-ex3.2, DALLE-ex3.3, ChatGPT-ex4, ChatGPT-ex | OpenAI node (AI section) |
| Read Binary Files LoadMP3 | Read/Write Files from Disk |
Nodes used (7)
- Manual Trigger
n8n-nodes-base.manualTrigger - OpenAI
n8n-nodes-base.openAi - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - HTML
n8n-nodes-base.html - Read Binary Files
n8n-nodes-base.readBinaryFiles
From the author
Primer workflow for OpenAI models: ChatGPT, DALLE-2, Whisper This workflow contains 5 examples on how to work with OpenAI API. - Transcribe voice into text via Whisper model (disabled, please put your own mp3 file with voice) - The old way of using OpenAI…