5 comments

  • Alex-Programs 4 hours ago
    This is really cool!

    I've done a lot of research into LLM translation for my product[0], and I'm currently working on a deep translation service that provides reliably human-level translations.

    I don't know what model you're using, but GPT-4.1 is probably the best for your use case - it's in the top few % for nearly every language, and has a low standard deviation, while also being relatively low latency and low cost.

    [0] https://nuenki.app

  • jmpavlec 1 hour ago
    Tried it with some Dutch, only getting "Unable to process correction" errors. Good idea but seems it need a bit more error handling.
  • sunbum 3 hours ago
    In the example text hjelmpe is not a word in Danish.
  • Aro_oj 6 hours ago
    First of all, 10 points for the dedication and perseverance! The website looks super professional and promising. What other languages can it help with? I am planning to learn Arabic. Also, are there options to choose between different dialects of a language?
    • lil_csom 5 hours ago
      Hey! It should work with all the languages as it auto-detect the target and the source language - however, it might need to be tuned the bit. Eg. if you write in arabic but use English wildcards, it should work okay! About the dialects actually I haven't thought of! I think you can provide it as context, however it's probably limited to what GPT knows as I don't integrate with any official trasnlators as of now :) Interesting use-case!
  • lil_csom 11 hours ago
    Also, yes the TTS doesn't work yet - I decided to share the MVP first before adding my Google billing account :P