Podcast to Notion: Auto-Transcribe and Publish Episodes Weekly

Build me an agent workflow that turns each new podcast or interview recording into a fully fleshed-out content entry in my Notion content library.

Trigger: cron, every Monday at 9am in my local timezone.

On each run, the agent should:

1. Call Google Drive List Files to find any audio files added to my 'Podcast Episodes' folder in the last 7 days. Use the Drive query language to filter on the folder's parent ID, a createdTime greater than 7 days ago, mimeType starting with audio/, and trashed = false. If there are no new files, exit cleanly without creating anything.

2. For each new audio file, call Google Drive Download File Content to fetch the raw bytes.

3. Call Deepgram Transcribe Pre-recorded Audio with the raw bytes as the request body. Enable diarization, paragraphs, smart formatting, and utterances. Use the nova-3 model. Keep the Deepgram response, the speaker-labeled transcript, and the paragraph timestamps for the next step.

4. From the transcript, generate: an episode title, a two-paragraph episode summary, a list of timestamped chapter markers derived from Deepgram's paragraph and topic boundaries (format MM:SS Chapter title), three pull quotes lifted verbatim from the transcript, and five social-ready snippets: one for LinkedIn, two for X (under 280 chars each), and two for the email newsletter (3 to 5 sentences each).

5. Call Notion Create a Page in my Content database. Map the generated fields to these properties: Title (episode title), Summary (the two-paragraph summary), Status (set to 'Draft'), Chapter Markers (rich text, one chapter per line), Pull Quote 1, Pull Quote 2, Pull Quote 3, LinkedIn Post, X Post 1, X Post 2, Newsletter Blurb 1, Newsletter Blurb 2, Source File (link to the Drive file), Recorded Date (the file's createdTime).

6. Call Notion Append Block Children on the page that was just created to add the full diarized transcript at the bottom. Use heading_2 'Full Transcript' followed by paragraph blocks, one per speaker turn, prefixed with the speaker label (e.g. 'Speaker 1: ...'). Keep paragraph blocks under Notion's 2000-character limit and split longer turns across multiple blocks.

7. Move on to the next audio file. Process them serially so a Deepgram failure on one episode doesn't kill the whole batch.

At the end of the run, log how many episodes were processed and any files that failed transcription.

I will provide: the Google Drive folder ID for 'Podcast Episodes', the Notion database ID for my Content library, and the exact property names in that database when I configure the workflow.

Additional information

What does this prompt do?

Picks up new audio files dropped into a 'Podcast Episodes' folder in Google Drive over the past week.
Transcribes each one with speaker labels, paragraphs, and clean formatting so quotes and chapters are usable straight out of the box.
Drafts the episode title, a two-paragraph summary, timestamped chapter markers, three pull quotes, and five social snippets sized for LinkedIn, X, and your newsletter.
Creates a new page in your Notion content database with all of that pre-filled, then drops the full diarized transcript at the bottom so editors can search it.

What do I need to use this?

A Google Drive account with a folder where you upload new podcast recordings
A Deepgram account for the transcription
A Notion workspace with a content database where new episode pages should land
Your Notion connection shared with the destination database

How can I customize it?

Change the schedule. Weekly on Monday at 9am is the default, but daily or every-other-Friday work just as well.
Point it at a different folder, or watch multiple folders if you produce more than one show.
Reshape the social snippets. Swap LinkedIn for Threads, ask for three newsletter blurbs instead of two, or have it draft a YouTube description for video episodes.
Adjust which Notion properties get filled in to match the columns your content team already uses.

Frequently asked questions

Will this work for video episodes too?

Yes. As long as the file in Google Drive contains an audio track, the transcription step handles it. The chapter markers and pull quotes come out the same way.

How accurate are the chapter markers?

They follow the natural topic breaks in the conversation, so a 45-minute episode usually gets 6 to 10 chapters. You can ask for fewer, more, or a fixed number in the prompt.

Do guests get identified by name?

The transcript labels speakers as Speaker 1, Speaker 2, and so on. You can tell the workflow who each speaker is for a given episode, or have it guess from the file name.

Where does the full transcript end up?

It's appended to the bottom of the new Notion page so the summary and snippets sit on top, and editors can still scroll down or search the full text.

What happens if I don't post any new episodes that week?

Nothing. The workflow looks at the folder, finds zero new files, and exits quietly without creating any pages.