How I AI

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

504 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