Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Please share an example of a two-speaker podcast that it has generated, add support for spoken Thai, and I will pay & use it weekly.
    by 55555
  • Cool! Curious to hear a sample. As any regular audiobook listener knows, having a great narrator is really key.
    by brunorsini
  • If you're on a Mac, `say -f book.txt -o book.aiff`, no API keys required.
    by Kwpolska
  • I use my hobby app PageHum to read short to medium articles in devices using MLX and Kokoro instead of. Give it a try if anyone interested in https://github.com/Mieraidihaimu/pagehum (Xcode 27+)
    by mier
  • Is "paste your OpenAI API key" the new form of "paste your credit card number with exp/code" for example, to check if its been compromised?
    by x______________
  • I love using https://convert.to.it/ for all of my converting needs; everything is client-side in the browser with over 400 file extension options to choose from.

    Source: https://github.com/p2r3/convert

    by subless
  • I did something very similar to this, for myself, but which takes a web page for an article, cleans up the text to preserve the article only, and converts it using TTS, then adds it to a cloud bucket with an RSS stream, and I use that RSS link as a podcast in Apple Podcast.
    by xenocratus
  • KeenLore is my emotive audiobook creator, which I've been working on for the past several months to help me narrate my sci-fi novel. Here's a slightly outdated demo video:

    https://www.youtube.com/watch?v=WAeHgE94rVo

    I've since added character ages (child to supercentenarian voices, consistent relative to their base adult voice), crowd chants (2 to 100 people works flawlessly), case sensitivity for character aliases (to help detect quotation attributions), custom phonetics, and English speaking characters can have a variety of accents applied. Will soon have Chatterbox driving the novel's narration. Screenshot:

    https://i.ibb.co/GffgfnCL/narrating.png

    It's self-hosted, fully local, based on software having permissive licenses and open weights. Runs on a lowly 8GB NVIDIA T1000 (and 96 GB of RAM).

    by thangalin

Explore Birbla archives