How to digest 36 weekly podcasts without spending 36 hours listening | Tomasz Tunguz (Theory Ventures)

632 snips

Aug 25, 2025

Tomasz Tunguz, founder of Theory Ventures and a well-known voice in the AI and data landscape, shares his innovative 'Parakeet Podcast Processor' to efficiently digest 36 audiobooks without the time commitment. He dives into creating a terminal-based system for transcribing and summarizing content, highlighting AI's role in generating actionable insights and investment strategies. He also discusses enhancing productivity with AI tools, while navigating the challenge of maintaining a personal writing style in automated content. Tune in for a tech-savvy approach to podcast consumption!

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

Parakeet Podcast Processor Workflow

Tomasz built a Parakeet Podcast Processor to read, download, convert, and transcribe 36 podcasts daily so he can read instead of listen.
He stores transcripts, extracts quotes, themes, investment theses, and generates daily summaries and tweet ideas.

ADVICE

Automate Audio-to-Text At Scale

Use local tools like FFMPEG and Parakeet (or Whisper) to convert audio to text and streamline transcription pipelines.
Store processing state in a local DuckDB so you can orchestrate daily summarization and avoid reprocessing.

INSIGHT

Powerful LLMs Reduce Cleanup Needs

Cleaning transcripts helped initially but large LLMs reduced the need for heavy cleanup for tasks like named-entity extraction.
Investing effort in stronger models often beats extensive preprocessing of noisy inputs.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Tomasz Tunguz is the founder of Theory Ventures, which invests in early-stage enterprise AI, data, and blockchain companies. In this episode, Tomasz reveals his custom-built “Parakeet Podcast Processor,” which helps him extract value from 36 podcasts weekly without spending 36 hours listening. He walks through his terminal-based workflow that downloads, transcribes, and summarizes podcast content, extracting key insights, investment theses, and even generating blog post drafts. We explore how AI enables hyper-personalized software experiences that weren’t feasible before recent advances in language models.

What you’ll learn:

1. How to build a terminal-based podcast processing system that downloads, transcribes, and extracts key insights from multiple podcasts daily

2. A workflow for using Nvidia’s Parakeet and other AI tools to clean transcripts and generate structured summaries of podcast content

3. How to extract actionable investment theses and company mentions from podcast transcripts using AI prompting techniques

4. A systematic approach to generating blog post drafts with AI that maintains your personal writing style through iterative feedback

5. Why using an “AP English teacher” grading system can help improve AI-generated content through multiple revision cycles

6. How to leverage Claude Code for maintaining and updating personal productivity tools with minimal friction

—

Brought to you by:

Notion—The best AI tools for work

Miro—A collaborative visual platform where your best work comes to life

—

25k giveaway:

To celebrate 25,000 YouTube followers, we’re doing a giveaway. Win a free year of my favorite AI products, including v0, Replit, Lovable, Bolt, Cursor, and, of course, ChatPRD, by leaving a rating and review on your favorite podcast app and subscribing to the podcast on YouTube. To enter: https://www.howiaipod.com/giveaway

—

Where to find Tomasz Tunguz:

Blog: https://tomtunguz.com/

Theory Ventures: https://theory.ventures/

LinkedIn: https://www.linkedin.com/in/tomasztunguz/

X: https://x.com/ttunguz

—

In this episode, we cover:

(00:00) Introduction to Tomasz Tunguz

(03:32) Overview of the podcast ripper system and its components

(05:06) Demonstration of the transcript cleaning process

(06:59) Extracting quotes, investment theses, and company mentions