Zoom ScribevsZoom Scribe Pro
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Scribe1.97% · 118ms
- Scribe Pro1.96% · 162ms
Zoom Scribe is ahead of Zoom Scribe Pro on time to first text and final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Pipecat Dataset WER1.97%1.96%
- Ocular Dataset WER4.88%4.84%
- Time to first text1.67s1.70s
- Final-text delay118ms162ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Scribe vs Scribe Pro FAQ
Which is more accurate, Zoom Scribe or Zoom Scribe Pro?
Zoom Scribe and Zoom Scribe Pro are too close to call on accuracy. On the 1,000 public Pipecat clips, Zoom Scribe scores 1.97% and Zoom Scribe Pro 1.96%, with likely ranges of 1.73 to 2.22% and 1.73 to 2.20%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Zoom Scribe scores 4.88% and Zoom Scribe Pro 4.84%, with likely ranges of 4.41 to 5.29% and 4.23 to 5.43%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Zoom Scribe and Zoom Scribe Pro are too close to call on accuracy. On the 1,000 public Pipecat clips, Zoom Scribe scores 1.97% and Zoom Scribe Pro 1.96%, with likely ranges of 1.73 to 2.22% and 1.73 to 2.20%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Zoom Scribe scores 4.88% and Zoom Scribe Pro 4.84%, with likely ranges of 4.41 to 5.29% and 4.23 to 5.43%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Zoom Scribe finishes the transcript 44ms sooner. Zoom Scribe has the final transcript 118ms after the speaker stops and Zoom Scribe Pro 162ms, at the median. Both are measured on the same 206 streamed turns.
Zoom Scribe finishes the transcript 44ms sooner, and the two are too close to call on real conversations. 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. Zoom Scribe shows first text after 1.67s and Zoom Scribe Pro after 1.70s, at the median, so Zoom Scribe is 31ms sooner.