Read content of word docx file

[Issac_Lavi]

I’m using version 1.86.1, on a cloud hosting

I’m trying to read binary data from a Word document. I used the Google Drive node to download the file and now I’m trying to extract the content from the binary data so I can send it to my AI agent. Since the “Move to binary” node no longer exists, I’m trying to use “Extract to file” to convert it from binary to JSON, but I don’t see any option in this node’s actions that can extract Word document binary data to JSON.

I tried to decompress the file with the Compression node to isolate and read the content of word/document.xml, but it seems like it cannot read the downloaded binary data.

I’m going back and forth with different solutions but no success.

Please help. Thanks!

I’m using version 1.86.1 on cloud hosting, using Mac OS

[mohamed3nan]

Hi @Issac_Lavi Welcome to n8n community

If it’s a Doc file and it’s already in your Google Drive, why not just use the Google Docs node to read the file?

[rbreen]

Hi @Issac_Lavi ,

You can convert the file to txt, then extract it with an extract node. Here’s a workflow.

Best,

Robert

[Issac_Lavi]

Hi @mohamed3nan, thanks for your response.
I also tried that approach, but the Google Docs node cannot read the file since it’s a Word document rather than a Google Doc. While the workflow trigger is “Google Drive - file created,” and my goal is to read the uploaded Word document for my agent (for translation or summarization), using the “GET document by ID or URL” operation returns this error:

Bad request - please check your parameters
This operation is not supported for this document.

I’m sorry, but I can’t share the workflow - I probably don’t have the right plan level for collaboration.

[Issac_Lavi]

Hi @rbreen . Thanks for your response.

I’ve tried this approach, but the text extraction isn’t working properly—the output consists of gibberish characters instead of the actual text.

[mohamed3nan]

Hi @Issac_Lavi
Since it doesn’t seem possible on the cloud version, here’s a simple solution: call this Google workspace API to convert the file from Word to Google Docs so you can read it.

You can use it with your existing Google Drive Authentication, and it should work.

Note: this method always leaves your original Word file in Drive and generates a separate Google Docs‑format copy.

If you need to clean up, you’ll have to delete the original yourself.

[Issac_Lavi]

Awesome ! it worked!

Thanks