The flow
Starts it 2Model 2Logic 8Service 2
The steps in the order they run, from what starts it.
- 1Webhook - Voice Note UploadedWebhookStarts it
- 2Manual Trigger - Test RunManual triggerStarts it
- 3OpenAI Chat ModelLm Chat Open AiModel
- 4Set - ConfigSetLogic
- 5AI - Clean Up & Summarize NoteChain LlmModel
- 6HTTP Request - Transcribe AudioHttp RequestService
- 7JS - Parse LLM Output & Build Note PayloadCodeLogic
- 8JS - Clean Transcript & Prepare LLM InputCodeLogic
- 9Wait - For Save ConfirmationWaitLogic
- 10Wait - For Transcript ReviewWaitLogic
- 11IF - Save ApprovedIfLogic
- 12IF - Review ApprovedIfLogic
- 13Slack - Send Voice Note SummarySlackService
- 14Set - Discarded/CancelledSetLogic
How it's built
- Starts on
- Another system calling it
- Steps
- 14, with 2 branches, 2 loops or waits
- Size
- Medium: a working afternoon
- Connects to
- Slack
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Slack account, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on another system calling it.
Does it use AI?
Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 14 steps is enough that you should read each one before running it.
How do I import it?
Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.
Before you run itNothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 14 steps before you point it at anything that matters.