15 comments

  • totetsu 2 days ago
    Neat. I was just looking for something like this for auto gating etc, for mixing podcast audio. Also phoneme level accuracy from something like this would be useful for realtime lipsync animation, and tools support pronunciation learning.
    • v7n 2 days ago
      I also recently looked into stuff like this for studying rap music across wildly different languages and styles and time periods to see what kinds of patterns emerge. Niche, but maybe one day we will get there.
  • spudlyo 18 hours ago
    How does this compare to using a model like facebook/wav2vec2-base960h for scoring at a 20ms per frame, and then something like torchaudio.functional.forced_align to map those frames onto the transcript words?

    I get pretty accurate results this way, along with some nudging heuristics based on the expected leading or trailing word sibilance.

    For multilingual work, facebook/mms-1b-all (trained on ~1100 languages) works extremely well, but is significantly slower on my CPU.

  • niwrad 18 hours ago
    This is great - I run an AI Video startup. We've been testing different solutions around this recently.

    How's the performance across different languages?

  • HOWLD 21 hours ago
    How does "free until tomorrow night" work? (or, on the page "free until Monday") - Is it just the $5 credit if signing up with a company email?
  • poxlr 8 hours ago
    woah, I think I can use it for deleting stops between words in videos and voice memos and such cant we?
  • demibabs 21 hours ago
    Cool! Does this work well with singing/music? If so this would be great for a project I’m doing.
  • mariusziskra 2 days ago
    [flagged]
  • ggm 22 hours ago
    Um and err and so and but but but editing might be good with this. well gooder. It's hard when the umbut runs into the word.
  • francuza9 2 days ago
    [dead]
  • palash76 12 hours ago
    [dead]
  • chmenegatti 22 hours ago
    [dead]
  • londons_explore 2 days ago
    The example use case really feels like making fake news and misleading edits easier...
    • xp84 20 hours ago
      At a certain point, blaming tools like AI for fake news and misleading information is like blaming electricity for it. Anybody left on Earth today who takes every video to be an authentic and faithful representation of a reality that actually happened should really get out from under the rock they’ve been under for the last four years.

      Yes, it is easier than ever to make fake content. No, no matter what the mainstream does, bad actors will attempt to fool people with this tech. The cat has been out of the bag for a long time.

  • dbbk 2 days ago
    [flagged]
    • xp84 20 hours ago
      The linked page discusses comparisons with it. It’s supposed to be better than elevenlabs.
  • imguienjoyer30 2 days ago
    [flagged]