How to Adapt Thomas Frank's ChatGPT Summarization Method for Obsidian Using Whisper API and Google Drive?

This topic was automatically generated from Slack. You can find the original thread here.

Adapted from Thomas Frank’s video about ChatGPT summarizing notes for Notion, I adapted this one for Obsidian. Will watch a folder for an audio file, transcribe with the Whisper API, then send the file back to my GDrive (Obsidian Vault) in markdown format. Prompts in the thread!
Trigger: New file in a specific Google Drive folder

  1. Download file
  2. Create transcription
  3. ChatGPT summarize body
  4. ChatGPT create title
  5. Drive create file from text

1 Like
Write a Title for the transcript that is under 15 words and contains no quotation marks

Then write: "---"

Write "Summary" as a Heading 2 (For example: ## Heading)

Write a summary of the provided transcript.

Then write: "---".

Then return a list of the main points in the provided transcript. Then return a list of action items. Then return a list of follow up questions. Then return a list of potential arguments against the transcript.

For each list, return a Heading 2 (For example: ## Heading) before writing the list items. Limit each list item to 100 words, and return no more than 5 points per list.



Write a Title for the transcript that is under 5 words, containing no quotation marks or special characters



Hi @user-1 thanks a bunch for this intiative.
With my little tech knowledge i tried to follow your instructions.
Test both with an mp3 and m4a files.

All good, until step “create_transcription” where i’m getting the following error.
Error - Request failed with status code 400
{“error”:{“message”:“Unrecognized file format. Supported formats: [‘flac’, ‘m4a’, ‘mp3’, ‘mp4’, ‘mpeg’, ‘mpga’, ‘oga’, ‘ogg’, ‘wav’, ‘webm’]”,“type”:“invalid_request_error”,“param”:null,“code”:null}}

PLEASE HELP me finish this.
Thank you!