Left gets fewer words wrong. Lower has the final text ready sooner.
AssemblyAI Universal 3.6 Pro is ahead of Zoom Scribe 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
Lower is better on every measure. Too close to call means the likely ranges overlap.
Both providers, every model: AssemblyAI vs Zoom
AssemblyAI Universal 3.6 Pro and Zoom Scribe are too close to call on accuracy. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 1.77% and Zoom Scribe 1.97%, with likely ranges of 1.55 to 2.00% and 1.73 to 2.22%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, AssemblyAI Universal 3.6 Pro scores 4.50% and Zoom Scribe 4.88%, with likely ranges of 3.66 to 5.34% and 4.41 to 5.29%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
AssemblyAI Universal 3.6 Pro and Zoom Scribe are too close to call on accuracy. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 1.77% and Zoom Scribe 1.97%, with likely ranges of 1.55 to 2.00% and 1.73 to 2.22%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, AssemblyAI Universal 3.6 Pro scores 4.50% and Zoom Scribe 4.88%, with likely ranges of 3.66 to 5.34% and 4.41 to 5.29%. 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 3.6 Pro finishes the transcript 27ms sooner. AssemblyAI Universal 3.6 Pro has the final transcript 91ms after the speaker stops and Zoom Scribe 118ms, at the median. Both are measured on the same 206 streamed turns.
AssemblyAI Universal 3.6 Pro finishes the transcript 27ms 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 3.6 Pro shows first text after 485ms and Zoom Scribe after 1.67s, at the median, so AssemblyAI Universal 3.6 Pro is 1.18s sooner.