Guide
How to get transcripts of 20VC videos
Founders and investors say the specific things on 20VC: the round size, the multiple, the mistake. Across hundreds of hour-long interviews, the text is the only practical way to find who said what.
Get every available transcript in three steps
- Paste the podcast link. BulkTranscripts detects whether it is a video, playlist, or channel automatically.
- Press Get transcripts. Videos are processed in parallel with live progress, and anything already in your library is served instantly from cache.
- Export. Download a ZIP with one file per video, or a single combined document — TXT, Markdown, SRT, VTT, CSV, JSON, or AI-ready.
What people do with 20VC transcripts
The common use is to compare what different investors say about the same question, like seed valuations or AI margins, with the guest and episode attached to every quote. Because the combined export carries each video's title, channel, date, and link in a header, an AI model can cite which video an answer came from instead of blending everything together.
About the 20VC archive
20VC (The Twenty Minute VC) is Harry Stebbings' interview show with venture investors and founders, running since 2015 and now well past 1,500 episodes on Apple Podcasts. Despite the name, the YouTube episodes in our sample average just over an hour. Every one of them came back with YouTube's auto-generated captions, so fund and company names are the words to double-check.
Questions the full transcript set can answer
Load the combined export into NotebookLM, ChatGPT or Claude and ask:
- What have investors on 20VC said about seed-stage valuations since 2024, and who said it?
- Which guests disagreed about whether AI application companies can keep their margins?
- List every founder who described their worst hiring mistake, with the episode link.
What 20VC looks like as text
Measured from 20VC videos our users have already transcribed, pulled from our production library on October 16, 2026. It is a sample of the archive, not the whole thing.
| Measure | Result | What it means |
|---|---|---|
| Videos already transcribed | 427 | Upload dates January 2022 to September 2026 |
| Hours of audio | 469 | Average 66 min, longest 117 min |
| Words per video | 12,888 on average | About 26 printed pages each |
| Speaking pace | 196 words a minute | Useful for estimating an episode you have not pulled yet |
| Caption source | 0 channel-uploaded, 427 auto-generated | Channel captions are preferred when both exist |
For sizing: 100 episodes at this length is roughly 1.3 million words and costs 100 credits, one per video. That is more than most AI chats will hold at once, so use the combined export in NotebookLM, or connect the MCP server and let the assistant fetch only the episodes a question needs.
Sources
Questions
Are 20VC transcripts auto-generated?
Every one of the 427 videos from 20VC in our library came back with YouTube's auto-generated captions, so expect the occasional misheard name. The words are there and searchable; proper nouns are where errors cluster.
Is there a limit on how many 20VC videos I can transcribe?
You can run a whole channel or playlist in one job. Large archives are processed in batches with live progress, and everything you have already pulled is cached so re-runs are instant.
Do I need to sign in?
No. Paste a link and go.
What if a video has no captions?
It is skipped and reported in the results, and the rest of the job continues. Videos with creator-written captions are preferred over auto-generated ones when both exist.
Can I get one file instead of hundreds?
Yes. Choose the combined export to get the entire channel or playlist as a single document, which is what you want for NotebookLM, ChatGPT, or Claude.