PodText.ai

AI

podcast transcript search

SHOW HN2023

219points
84comments
#251of 3,109 in 2023
Top 9%of 2023 by points

How HN took it

CuriousMostly questions and neutral comments

11 positive, 24 neutral or asking, 0 mixed, 12 critical, out of 47 comments about the project. Thread score +0.03.

Idea: 7 for, 4 againstExecution: 1 for, 4 againstDesign: 2 for, 0 againstPricing: 0 for, 2 againstDocs: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Search and word highlighting feel fast and useful

    From 2 comments
    • Looks very cool! Besides the search, which works great and feels like a powerful tool, I like how snappy the word highlighting is in the transcripts. Can you elaborate a bit on…
      marcelfahle on HN
    • This is a game-changer for topic research. Thank you! I also agree that this will be a valuable resource for potential business sponsors and worth the money. One note, I like…
      moserch on HN
  • Useful for sponsors and topic research

    From 2 comments
    • This is a really interesting project with a lot of potential. If I were a sponsor looking for a podcast I would want my search process to look something like this: - Search for a…
      lappa on HN
    • This is a game-changer for topic research. Thank you! I also agree that this will be a valuable resource for potential business sponsors and worth the money. One note, I like…
      moserch on HN

Objections

  • Fuzzy search returns irrelevant matches and misses exact phrases

    From 4 comments
    • Really interesting service; well done! Looking forward to seeing how it will evolve. Quick feedback: it seems you're using fuzzy search, which may or may not be what the user…
      guiambros on HN
    • Nice idea but it didn't work for me... you need to look into why "poppadoms or bread" isn't turning up any results. It's one of the lines in every episode of the Off Menu…
      idk1 on HN
    • This is neat, but would it be possible to search for a multi-word phrase? If I search for a sequence of words I just get results that match one or more of the words but not the…
      skykooler on HN
    • How can I search for a full name or phrase? Something like "Steve Jobs"? Now I would get Steve and Jobs results.
      mosselman on HN
  • Limited podcast coverage; many popular shows missing

    From 3 comments
    • Seems like Chapo Trap House and The Adam Friedland Show are inexplicably unrepresented not only here but on other similar webapps linked elsewhere in this thread... Strange,…
      anon25783 on HN
    • I couldn't find either of Jim Cornette podcasts, tiger belly, flagrant, brilliant idiots, and Matt and Shane's secret podcast which I think is number 1 on Patreon. I would assume…
      dec0dedab0de on HN
    • Very neat! Is it possible to browse by topic instead of by podcast? You mentioned 25k podcast episodes but right now I can only browse ~100 of them or so unless I come up with…
      kevmo314 on HN
  • Copyright concerns over transcripts of podcasts

    From 2 comments
    • Do you get permission from podcast creators? Because these transcripts are probably derivative works.
      paulryanrogers on HN
    • Hate to be that guy, but is this legal? I would assume to do something like this you would need to have permission from each of the copyright holders.
      dec0dedab0de on HN
  • Transcription costs are very high at this scale

    From 3 comments
    • How are you guys affording the transcription bills? 25,000 episodes at 1 hour long, could cost 30,000 USD at a conservative market rate. Are you guys self funded?
      Ferdows-ip on HN
    • The transcription price would be big for 25,000 episodes at 1 hour long. That's like 30,000 USD. How are you guys funding this?
      Ferdows-ip on HN
    • Do I understand correctly banana pricing is that it costs $1.87 per hour, so the hour of audio with large model costs you about $1? Thats probably a bit too expensive compared to…
      nshm on HN

Requests

  • Exact phrase and multi-word search

    From 4 comments
    • Building out the search a little more to support exact matches would also be super useful in this flow. For example, I've been on several podcasts talking about Notebook.ai, but…
      drusepth on HN
    • This is neat, but would it be possible to search for a multi-word phrase? If I search for a sequence of words I just get results that match one or more of the words but not the…
      skykooler on HN
    • How can I search for a full name or phrase? Something like "Steve Jobs"? Now I would get Steve and Jobs results.
      mosselman on HN
    • This is amazing. How do you search for two terms at once? e.g. "aboriginal" and "origin". Doesn't seem possible to require both terms are present.
      mritchie712 on HN
  • Keyword alerts for terms or speakers

    From 1 comment
    • If you want to grow your audience user-wise, allowing people to add alerts on specific terms would be pretty cool. There's a set of people I always enjoy listening to whenever…
      lxm on HN
  • Speaker diarization

    From 1 comment
    • I thought about making something like this, but one important part - which seems to be missing here - is speaker diarization (identify who says what.) In a world of increasing…
      sva_ on HN
  • Browse by topic and jump to matched position in transcript

    From 2 comments
    • Very neat! Is it possible to browse by topic instead of by podcast? You mentioned 25k podcast episodes but right now I can only browse ~100 of them or so unless I come up with…
      kevmo314 on HN
    • Nice work! It would be great if after clicking on the text within the podcast that matches my term, I was brought to that section of the transcript rather than to the beginning.
      jcowdy on HN

Questions

  • How is transcription being funded and what models are used

    From 3 comments
    • How are you guys affording the transcription bills? 25,000 episodes at 1 hour long, could cost 30,000 USD at a conservative market rate. Are you guys self funded?
      Ferdows-ip on HN
    • What software do you use to transcribe the speech? Whisper?
      BonoboIO on HN
    • Have you tweaked Whisper in any specific ways to improve accuracy?
      71a54xd on HN
  • How are podcasts discovered for indexing

    From 1 comment
  • Is it legal to transcribe podcasts without permission

    From 2 comments
    • Do you get permission from podcast creators? Because these transcripts are probably derivative works.
      paulryanrogers on HN
    • Hate to be that guy, but is this legal? I would assume to do something like this you would need to have permission from each of the copyright holders.
      dec0dedab0de on HN

Alternatives named

  • ListenNotes

    From 2 comments
    • Surprised to see how many other small projects doing this same thing there are. Kinda seems like a solved problem with ListenNotes. Not affiliated, but I use the service a lot…
      culi on HN
    • I'd echo this. ListenNotes API is great and I thought podcast search was already solved for devs. I've always enjoyed this question on their FAQ that gives some tips for…
      jonmc12 on HN
  • Podscribe

    From 1 comment
    • Please take it as encouragement that this is a real business and not discouragement that it's been done but there are similar products in the market. We use podscribe at my…
      tootie on HN
  • Snipd

    From 1 comment
    • If anyone is interested, there's a podcast app called Snipd that integrates transcription. They also use AI to create chapters and snippets. It then creates a feed of snippets,…
      rubslopes on HN
  • Steno.ai and Podscript.ai

    From 2 comments
  • Podscription.app

    From 1 comment
    • Here's my crack at a podcast transcription website: https://podscription.app I made this while unemployed and the skills I learned from making it helped me land my new job!
      SCUSKU on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/34727695)