vo.codes

AI

text to speech

SHOW HN2020

Legend

vo.codes

Neural text to speech with dozens of celebrity voices

vocodes.com

#text to speech#voice cloning#neural tts#celebrity voices

462points
165comments
#58of 3,028 in 2020
Top 2%of 2020 by points

How HN took it

CuriousMostly questions and neutral comments

22 positive, 48 neutral or asking, 2 mixed, 15 critical, out of 87 comments about the project. Thread score +0.10.

Idea: 8 for, 2 againstPerformance: 1 for, 5 againstExecution: 3 for, 2 againstDocs: 1 for, 1 againstPrivacy: 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

  • Voices are uncannily accurate

    From 1 comment
    • Having met some of the people on there, this is uncannily accurate, especially in the High Quality voices. Well done!
      martinesko36 on HN
  • Impressive results

    From 1 comment

Objections

  • Site errors and rate limiting under HN load

    From 3 comments
    • Guess the server is overloaded now. All I'm seeing are errors. Tip: It's a cool idea to put some ready made samples under the photos. A lot of people like myself only want to…
      superasn on HN
    • I keep getting hit with the rate limiter so I wasn't able to try it :( > There was an error and I still haven't implemented retry to make it invisible. You can absolutely submit…
      blisseyGo on HN
    • I think the site's being hugged to death by HN. I can't get any of the voices to work, they all error out.
      nojvek on HN
  • Legal risk from celebrity voice use

    From 2 comments
    • I think you're going to have legal risks with a project like this. At some point a celebrity is going to sue and we'll find out what the law decides.
      Dramatize on HN
    • I'm not a lawyer, but I think we're entering into a legal gray area. There are the existing frameworks of copyright, parody, free speech, slander, libel, etc. that are all…
      echelon on HN
  • Deepfake and security abuse concerns

    From 2 comments
    • That's super cool. I am worried about the potential abuse of this service, are there any existing services that can help to identify audio deep fakes like this one is for making…
      searchableguy on HN
    • I assume that if somebody had physically lost their ability to speak, it would now be possible to generate a pretty reasonable synthetic voice. Should we all be archiving a…
      iamthemonster on HN

Requests

  • Add female voices

    From 2 comments
    • You haven't done very many female voices. Is this a limitation of the modeling process?
      ReedJessen on HN
    • Is there a reason why no female voice is available in this great project? Do we have more data on male speech than female speech?
      valaymerick on HN
  • Add more celebrity voices such as Christopher Walken, Steve Jobs, Majel Barrett

    From 3 comments
  • Pre-made audio samples under photos

    From 1 comment
    • Guess the server is overloaded now. All I'm seeing are errors. Tip: It's a cool idea to put some ready made samples under the photos. A lot of people like myself only want to…
      superasn on HN

Questions

  • How the models were trained and how long it takes

    From 2 comments
    • How long does it take to generate a good quality voice?
      galuggus on HN
    • Very cool, and easy to use! Can you give some more info on how you generated the models? I'm also interested in the tech stack you're using to implement this webapp... Would love…
      sunsetMurk on HN
  • Whether voice conversion is planned

    From 1 comment
    • I've built a lot of celebrity text to speech models and host them online: https://vo.codes It has celebrities like Sir David Attenborough and Arnold Schwarzenegger, a bunch of…
      echelon on HN

Alternatives named

  • Mellotron

    From 1 comment
    • Thanks! There are a lot of neat research threads ongoing in terms of generating vocals. Nvidia published Mellotron (code + paper + models), and the results are promising:…
      echelon on HN
  • Tacotron 2 with WaveGlow

    From 1 comment
    • I can make a blog post later, but at a high level: A rust TTS server hosts two models: a mel inference model and a mel inversion model. The ones I'm using are glow-tts and…
      echelon on HN
  • Resemblyzer

    From 1 comment
    • That's super cool. I am worried about the potential abuse of this service, are there any existing services that can help to identify audio deep fakes like this one is for making…
      searchableguy 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/23965787)