GPT-4o Transcribe vs Zoom Scribe Pro v2.1

Compare

Accuracy and speed

Left gets fewer words wrong. Lower has the final text ready sooner.

Accurate and fast0ms200ms400ms600ms800ms0%2%4%6%Words wrong on clean audio (Pipecat WER)
  • 4o Transcribe3.90% · 652ms
  • Scribe Pro v2.11.55% · 178ms

Zoom Scribe Pro v2.1 is ahead of GPT-4o Transcribe on both datasets together, the Pipecat Dataset, the Ocular Dataset and final-text delay.

Last updated Methodology by Dileep Chagam

Who is better at what

4o TranscribeScribe Pro v2.1
  • Overall WER6.85%2.35%
  • Pipecat Dataset WER3.90%1.55%
  • Ocular Dataset WER12.45%3.87%
  • Time to first textn/a793ms
  • Final-text delay652ms178ms

Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide covers testing OpenAI Realtime API voice agents.

Clip by clip

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.

4o TranscribeScribe Pro v2.1
  • ELO rating873834–934 · rank 22–2310461029–1053 · rank 1–10
  • Expected win rate27%73%
  • Ocular turns WER · 109 draws of 1946 won79 won
  • Pipecat WER · 826 draws of 99931 won142 won
  • Semantic WER · 157 draws of 1944 won33 won
  • Phone line · 101 draws of 1983 won94 won
  • Call-center noise · 59 draws of 1985 won134 won
  • Babble noise · 61 draws of 19814 won123 won
  • TV noise · 83 draws of 19828 won87 won
  • Reverb · 90 draws of 1989 won99 won
  • Short replies · 36 draws of 693 won30 won
  • Entities · 45 draws of 480 won3 won

Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out

4o Transcribe vs Scribe Pro v2.1 FAQ

  • Zoom Scribe Pro v2.1 is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT-4o Transcribe scores 6.85% and Zoom Scribe Pro v2.1 2.35%, so Zoom Scribe Pro v2.1 makes fewer errors by 4.50 points. On the 300 licensed Ocular turns, GPT-4o Transcribe scores 3.90% and Zoom Scribe Pro v2.1 1.55%, so Zoom Scribe Pro v2.1 makes fewer errors by 2.36 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Final-text delay was not measured for one or both, so speed cannot be compared. Both are measured on the same 206 streamed turns.

  • Zoom Scribe Pro v2.1 makes fewer errors on real conversations, and the two are not separated on speed. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.

  • Only Zoom Scribe Pro v2.1. GPT-4o Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.