freesubtitles.ai

AI

speech transcription

SHOW HN2022

224points
129comments
#237of 2,570 in 2022
Top 10%of 2022 by points

How HN took it

MixedNo clear lean

17 positive, 26 neutral or asking, 4 mixed, 10 critical, out of 57 comments about the project. Thread score +0.13.

Execution: 3 for, 6 againstPerformance: 3 for, 3 againstIdea: 5 for, 0 againstPricing: 0 for, 1 againstDocs: 1 for, 0 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

  • Whisper transcription accuracy is strong, especially with the large model

    From 3 comments
    • I (used to) use simonsaysai.com to generate subtitles and they had the functionality to input specialized vocabulary, so I suppose it's possible in some sense but I don't know…
      mayeaux on HN
    • Yeah I was paying $100/month for transcription services and turns out Whisper with the large model was much more accurate, and I didn't like the UI, I much prefer to just use…
      mayeaux on HN
    • I've been running whisper in the terminal with Python and I've found whisper surprisingly accurate with the transcription even from Chinese. Just given your site a try, nicely…
      si_164 on HN
  • Cheaper than paid transcription services

    From 2 comments
    • Yeah I was paying $100/month for transcription services and turns out Whisper with the large model was much more accurate, and I didn't like the UI, I much prefer to just use…
      mayeaux on HN
    • Right now the limit is 100MB because of Cloudflare, no length limit, costs $1.30/h to run this, that's enough for a 2x RTX A6000 on Vast.ai can you check out the specs there
      mayeaux on HN

Objections

  • Queue and upload site hung or failed for users

    From 3 comments
    • This site hung basically every time I tried to use it. Only one out of nine attempts I made resulted in the page even decrementing the queue count. Curious if you could just…
      fiat_fandango on HN
    • Should this have the “Show HN” tag? Also, labels’ [for] attributes are all "file" instead of "language" and "model", so all labels trigger the file selection dialog on click :-)…
      notpushkin on HN
    • Yeah I apologize, the queue is a little messed up. It's not showing your progress properly and it's not stopping people's processing if they left (their websocket dies). I'm…
      mayeaux on HN
  • No progress indicator on processing page

    From 1 comment
    • I've been running whisper in the terminal with Python and I've found whisper surprisingly accurate with the transcription even from Chinese. Just given your site a try, nicely…
      si_164 on HN
  • Upload size limited to 100MB

    From 1 comment
    • Right now the limit is 100MB because of Cloudflare, no length limit, costs $1.30/h to run this, that's enough for a 2x RTX A6000 on Vast.ai can you check out the specs there
      mayeaux on HN

Requests

  • Progress indicator during processing

    From 2 comments
    • I've been running whisper in the terminal with Python and I've found whisper surprisingly accurate with the transcription even from Chinese. Just given your site a try, nicely…
      si_164 on HN
    • Thanks! I wrote it for myself over a weekend and have really enjoyed it ever since I'm glad others were able to get something out of it! It seems to run pretty well but I have…
      mayeaux on HN
  • Dropdowns instead of free text for language and model inputs

    From 1 comment
    • Shouldn't the language and model inputs be dropdowns instead of text input? I'm going to hope/assume you're doing some sort of sanitisation on those inputs. Additionally,…
      Namidairo on HN
  • Support for speaker diarization

    From 1 comment
    • Free startup idea: Use Whisper with pyannote-audio[0]’s speaker diarization. Upload a recording, get back a multi-speaker annotated transcription. Make a JSON API and I’ll be…
      jw1224 on HN

Questions

  • Maximum audio length and hosting costs

    From 1 comment
    • What is the maximum length of audio allowed? What are your costs in running this? Are the hardware requirements substantial?
      rexreed on HN
  • How well Whisper handles non-English languages

    From 1 comment
    • I didn't manage to transcribe anything (it just doesn't remember that I submitted anything), but whatever, I didn't need to anyway. I just wanted to ask: how good is Whisper with…
      krick on HN

Alternatives named

  • whisper.cpp for local transcription

    From 1 comment
    • This is a cool project. I’ve been very happy with whisper as an alternative to otter; it works better and solves real problems for me. I feel compelled to point out whisper.cpp.…
      n8cpdx on HN
  • Otter

    From 1 comment
    • This is a cool project. I’ve been very happy with whisper as an alternative to otter; it works better and solves real problems for me. I feel compelled to point out whisper.cpp.…
      n8cpdx on HN
  • Read.ai

    From 1 comment
    • There’s a lot of startups starting in the space offering transcription. Read.ai - https://www.read.ai/transcription Provides transcription & diarization and the bot integrates…
      lettergram on HN
  • Simonsays.ai

    From 1 comment
    • I (used to) use simonsaysai.com to generate subtitles and they had the functionality to input specialized vocabulary, so I suppose it's possible in some sense but I don't know…
      mayeaux on HN
  • Vosk

    From 1 comment
    • Exciting to see. Curious if there was a benefit to using whisper over something like vosk which can transcribe on mobile device pretty decently. Whisper has other interesting…
      j45 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/33663486)