Skip to content

New transcription model

Pinecast now uses a new transcription AI model, from the same vendor.

The new model brings some great improvements:

  1. For speaker labels (noting who is talking), the new model is almost twice as good on a variety of benchmarks.
  2. The timing of words in your transcripts are now slightly more accurate.
  3. You’ll get more accurate transcription of numbers, showing 12:50 instead of twelve fifty when talking about time.
  4. The accuracy of transcription is broadly improved across all of the supported langauges.
  5. 14 new languages are now supported, including Urdu, Russian, Korean, Catalan, Galician, Romanian, Estonian, Persian, Cantonese, Afrikaans, Marathi, Zulu, Xhosa, and Norwegian Nynorsk.