Left gets fewer words wrong. Lower has the final text ready sooner.
Zoom Scribe Pro v2.1 is ahead on both datasets together and final-text delay, and AssemblyAI Universal 3.5 Pro on time to first text. The Pipecat Dataset and The Ocular Dataset are too close to call. AssemblyAI Universal 3.5 Pro has a newer release: AssemblyAI Universal 3.6 Pro vs Zoom Scribe Pro v2.1.
Last updated Methodology by Dileep Chagam
Lower is better on every measure. Too close to call means the likely ranges overlap.
On every clip both models were scored on, the lower WER wins, and WERs within 5 points of each other are a draw; in the rating, a wider win counts for more. Expected win rate is what the two ELO ratings predict for a match.
Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out
Zoom Scribe Pro v2.1 is more accurate on the public clips. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.5 Pro scores 2.72% and Zoom Scribe Pro v2.1 2.35%, so Zoom Scribe Pro v2.1 makes fewer errors by 0.37 points. On the 300 licensed Ocular turns, AssemblyAI Universal 3.5 Pro scores 1.93% and Zoom Scribe Pro v2.1 1.55%, with likely ranges of 1.69 to 2.18% and 1.35 to 1.75%. 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 Pro v2.1 is more accurate on the public clips. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.5 Pro scores 2.72% and Zoom Scribe Pro v2.1 2.35%, so Zoom Scribe Pro v2.1 makes fewer errors by 0.37 points. On the 300 licensed Ocular turns, AssemblyAI Universal 3.5 Pro scores 1.93% and Zoom Scribe Pro v2.1 1.55%, with likely ranges of 1.69 to 2.18% and 1.35 to 1.75%. 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. AssemblyAI Universal 3.5 Pro finishes the transcript 304ms sooner. AssemblyAI Universal 3.5 Pro has the final transcript 489ms after the speaker stops and Zoom Scribe Pro v2.1 793ms, at the median. Both are measured on the same 206 streamed turns.
AssemblyAI Universal 3.5 Pro finishes the transcript 304ms 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. AssemblyAI Universal 3.5 Pro shows first text after 4.23% and Zoom Scribe Pro v2.1 after 3.87%, at the median.
Cekura runs these simulated calls on your agent and scores every one.