Google Drive to Chatwork, meeting notes everyone finds
Meeting ends, and then the real work starts. Someone hunts down the recording, someone else “quickly” transcribes it, and the action items end up buried in a chat thread that disappears by tomorrow.
Project managers feel this every week. So do operations leads trying to keep delivery tight, and agency owners who need client-ready notes without a late-night rewrite. This Drive Chatwork minutes automation turns a raw recording into structured minutes your team can actually find and use.
You’ll see how the workflow catches new recordings in Google Drive, runs transcription and minutes generation with OpenAI, saves a clean document back to Drive, then posts the summary straight into Chatwork.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Google Drive to Chatwork, meeting notes everyone finds
flowchart LR
subgraph sg0["Google Drive Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Google Drive Trigger", pos: "b", h: 48 }
n1@{ icon: "mdi:cog", form: "rounded", label: "Google Drive", pos: "b", h: 48 }
n2@{ icon: "mdi:robot", form: "rounded", label: "OpenAI", pos: "b", h: 48 }
n3@{ icon: "mdi:robot", form: "rounded", label: "OpenAI 2", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Upload file", pos: "b", h: 48 }
n5@{ icon: "mdi:cog", form: "rounded", label: "Convert to File", pos: "b", h: 48 }
n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Chatwork Notification"]
n2 --> n3
n3 --> n5
n4 --> n6
n1 --> n2
n5 --> n4
n0 --> n1
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n0 trigger
class n2,n3 ai
class n6 api
classDef customIcon fill:none,stroke:none
class n6 customIcon
The Problem: Meeting recordings don’t turn into usable minutes
Recordings are easy to create and weirdly hard to use. They sit in a Drive folder with names like “Meeting (3).mp4,” and if someone misses the call, they’re stuck scrubbing through 45 minutes just to learn the one decision that mattered. Even when someone does write notes, they’re often incomplete because the note-taker was also participating, presenting, or troubleshooting. Then you get the follow-up messages: “What did we decide?” “Who owns this?” “Is there a link?” It’s not one big failure. It’s constant small friction that burns time and makes teams slower than they need to be.
Here’s where it breaks down in real life.
- People spend about an hour per meeting turning audio into something readable, and it still ends up inconsistent.
- Action items get lost because the “notes” are a wall of text with no structure.
- The recording link is shared late or not at all, so stakeholders rely on secondhand summaries.
- When you do need to find a decision later, you’re stuck searching chat history and guessing filenames.
The Solution: Turn Drive recordings into Chatwork-ready minutes
This workflow watches a specific Google Drive folder for new meeting recordings. The moment a file lands there, n8n downloads it and sends the audio to OpenAI for transcription, producing a full text transcript you can reference later. Next, a second AI step turns that transcript into structured meeting minutes that read like something a human would send to a client or executive team. The workflow then converts those minutes into a document file (commonly a .txt, and it can be adapted for .docx), saves it back into a designated Drive folder with a timestamped name, and finally posts a formatted update to your Chatwork room so everyone sees the outcomes immediately. No chasing people. No “who has the notes?” scramble.
The workflow starts with a new file upload trigger in Google Drive. From there, it transcribes the recording and generates organized minutes with headings, decisions, and action items. Finally, it stores the final file in Drive and pushes the summary into Chatwork for instant visibility.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say your team runs 4 meetings a week and each one needs minutes shared in Chatwork. Manually, a realistic split is 30 minutes to download and organize the file, about 30 minutes to transcribe or clean up a transcript, and another 30 minutes to rewrite into readable minutes, so around 2 hours per meeting. With this workflow, you drop the recording into the right Google Drive folder (about 1 minute), then the system transcribes, summarizes, saves the file, and posts to Chatwork automatically. You still might skim the output, but you’re reviewing minutes instead of creating them from scratch.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Google Drive to store recordings and save minutes files.
- Chatwork to post minutes into the right room.
- OpenAI API key (get it from the OpenAI API dashboard)
Skill level: Intermediate. You will connect accounts, add API keys, and paste a Chatwork room ID without writing code.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A new recording lands in Google Drive. The workflow monitors one folder, so you can standardize where recordings go (Google Meet, Zoom, and Teams exports all work as long as they end up there).
The file is pulled down for transcription. n8n downloads the recording in the right format so OpenAI can generate a high-quality transcript instead of a messy partial.
AI turns raw conversation into structured minutes. First you get a transcript, then a second pass produces clean minutes with headings, key points, decisions, and action items. Honestly, the second step is where most of the “value” lives because it’s what makes the output skimmable.
Minutes are saved and shared automatically. The workflow converts the minutes into a document file, uploads it to a Drive folder with a timestamped filename, and posts a formatted summary into your Chatwork room via HTTP Request.
You can easily modify the minutes format to match your internal template, then route different meeting types to different Drive folders based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Google Drive Trigger
Set up the workflow to watch a specific Google Drive folder for new recordings.
- Add and open Drive File Added Trigger.
- Set Event to
fileCreated. - Set Trigger On to
specificFolderand select the folder in Folder To Watch (currently[YOUR_ID]). - Review Poll Times set to
everyHourat minute59. - Credential Required: Connect your
googleDriveOAuth2Apicredentials.
[YOUR_ID] with the actual Google Drive folder ID, or the trigger will never fire.Step 2: Connect Google Drive for Recording Download & Upload
Configure file handling so the new recording is downloaded and the final minutes are uploaded back to Drive.
- Open Download Drive Recording and set Operation to
download. - Set File ID to
{{ $json.id }}. - Set Options → File Name to
{{ $json.originalFilename }}and Binary Property Name todata. - Credential Required: Connect your
googleDriveOAuth2Apicredentials for Download Drive Recording. - Open Upload Minutes File and set Name to
{{ $now.format('yyyy-MM-dd _hhmmss') }}. docx. - Set Drive to
My Driveand select the destination Folder ID (currently[YOUR_ID]). - Credential Required: Connect your
googleDriveOAuth2Apicredentials for Upload Minutes File.
Step 3: Set Up the AI Processing Nodes
Transcribe the audio and generate meeting minutes using OpenAI.
- Open AI Audio Transcriber and set Resource to
audioand Operation totranscribe. - Credential Required: Connect your
openAiApicredentials for AI Audio Transcriber. - Open Meeting Minutes Generator and confirm the model is set to
gpt-5. - In Messages, ensure the user prompt includes the expression
{{ $now }}and the transcript from{{ $('AI Audio Transcriber').item.json.text }}. - Credential Required: Connect your
openAiApicredentials for Meeting Minutes Generator.
Step 4: Configure the Output and Notifications
Convert the generated minutes to a text file, upload it, and post a Chatwork notification.
- Open Text Document Converter and set Operation to
toText. - Set Source Property to
message.contentto convert the AI response text. - Open Chatwork Status Alert and set Method to
POST. - Set Content Type to
form-urlencodedand enable Send Body. - Add a body parameter named body with value
[info][title]自動通知[/title]議事録の作成が完了しました。[/info] {{ $('Meeting Minutes Generator').item.json.message.content }}. - Credential Required: Connect your
httpHeaderAuthcredentials for Chatwork Status Alert.
Step 5: Test and Activate Your Workflow
Validate the end-to-end flow before turning it on in production.
- Upload a new audio file into the watched Google Drive folder to trigger Drive File Added Trigger.
- Manually click Execute Workflow to confirm each node runs in sequence.
- Verify the transcript is generated in AI Audio Transcriber and that Meeting Minutes Generator returns a Japanese meeting minutes draft.
- Confirm a
.docxfile appears in the destination Drive folder from Upload Minutes File. - Check Chatwork for the notification sent by Chatwork Status Alert.
- When everything looks correct, toggle the workflow Active in n8n.
Common Gotchas
- Google Drive permissions matter more than people expect. If the trigger fires but downloads fail, check the connected Google account in n8n and confirm it has access to the monitored folder (and the destination folder for uploads).
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Chatwork tokens can be valid but under-scoped. If the post fails, verify your API token and confirm the room ID is correct in the HTTP Request settings, because a single digit off looks like “random” API failure.
Frequently Asked Questions
About 30 minutes if your Google Drive, OpenAI, and Chatwork accounts are ready.
No. You’ll mainly connect accounts, paste API keys, and choose the right Drive folders. The logic is already built into the n8n workflow.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI API usage for transcription and summarization (often just a few dollars a month for small teams).
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, and it’s a common tweak. You can adjust the Meeting Minutes Generator prompt to produce different formats for sales calls, internal standups, or client reviews. Many teams also add an If condition after the Drive trigger to route files into different output folders, and change the Chatwork message template in the HTTP Request step to match each audience.
Usually it’s permissions or an expired login. Reconnect Google Drive in n8n credentials, then confirm the account can access both the “watched” folder and the upload destination folder. If the recording was shared from another workspace, make sure you’re not monitoring a shortcut that your integration can’t read reliably.
A typical small team can run dozens of recordings a week without issues, as long as your n8n and OpenAI limits are sized for it.
Often, yes, because this workflow has two AI stages (transcription and structured minutes) and benefits from more flexible logic. n8n makes it easier to control file handling, retries, and branching without paying extra for every “step.” You can also self-host, which removes execution caps and keeps recordings processing inside your own environment. Zapier or Make can still work if your version is very simple, but long recordings and file handling can get awkward fast. If you want help picking the right route, Talk to an automation expert.
Once this is running, meeting minutes stop being a recurring chore and start being a reliable output. The workflow handles the repetitive parts so your team can focus on decisions and follow-through.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
