Left gets fewer words wrong. Lower has the final text ready sooner.
Cartesia Ink 2 is ahead on the Ocular Dataset and time to first text, and Zoom Scribe on final-text delay. The Pipecat Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Lower is better on every measure. Too close to call means the likely ranges overlap.
Cartesia Ink 2 is more accurate on real conversations. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and Zoom Scribe 1.97%, with likely ranges of 2.13 to 2.65% and 1.73 to 2.22%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Zoom Scribe 4.88%, so Cartesia Ink 2 makes fewer errors by 1.79 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Cartesia Ink 2 is more accurate on real conversations. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and Zoom Scribe 1.97%, with likely ranges of 2.13 to 2.65% and 1.73 to 2.22%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Zoom Scribe 4.88%, so Cartesia Ink 2 makes fewer errors by 1.79 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Zoom Scribe finishes the transcript 5ms sooner. Cartesia Ink 2 has the final transcript 123ms after the speaker stops and Zoom Scribe 118ms, at the median. Both are measured on the same 206 streamed turns.
It is a trade-off. Cartesia Ink 2 makes fewer errors on real conversations, while Zoom Scribe finishes the transcript 5ms sooner. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Yes, both return partial text before the speaker stops. Cartesia Ink 2 shows first text after 1.51s and Zoom Scribe after 1.67s, at the median, so Cartesia Ink 2 is 157ms sooner.