Grok Voice Transcribe 2.0

(x.ai)

20 points | by vertigoruntime 1 hour ago

5 comments

  • nomel 1 hour ago
    > Word-level timestamps. Each word has precise start/end times and confidence scores.

    Neat. This is missing from many models.

    • throwaway89201 33 minutes ago
      Mistral STT offers it, which is an open model.
  • xnx 41 minutes ago
    $0.10/hour is a good price vs $0.30/hour for Gemini Transcribe 3.5.
  • exizt88 1 hour ago
    I don't understand how these benchmarks get things so wrong. Nova-3 is by far the best model on the market in WER. Azure's STT is atrocious. And yet every benchmark rates Azure's STT higher than Nova-3's.
    • mistic92 53 minutes ago
      Mai 2 transcribe is giving me better results than nova
  • mistic92 53 minutes ago
    If only they had ZDR
  • bigyabai 1 hour ago
    No weights, sadly. Bit of a nothingburger release.