GPT Realtime Whisper 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)
  • Realtime Whisper2.16% · 543ms
  • Scribe Pro v2.11.55% · 178ms

Zoom Scribe Pro v2.1 is ahead of GPT Realtime Whisper on both datasets together, the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

Realtime WhisperScribe Pro v2.1
  • Overall WER2.63%2.35%
  • Pipecat Dataset WER2.16%1.55%
  • Ocular Dataset WER3.53%3.87%
  • Time to first text1.38s793ms
  • Final-text delay543ms178ms

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.

Realtime WhisperScribe Pro v2.1
  • ELO rating10091005–1020 · rank 5–1610461029–1053 · rank 1–10
  • Expected win rate45%55%
  • Ocular turns WER · 157 draws of 19816 won25 won
  • Pipecat WER · 895 draws of 99935 won69 won
  • Semantic WER · 187 draws of 1986 won5 won
  • Phone line · 156 draws of 19810 won32 won
  • Call-center noise · 120 draws of 19812 won66 won
  • Babble noise · 99 draws of 19824 won75 won
  • TV noise · 114 draws of 19859 won25 won
  • Reverb · 129 draws of 19814 won55 won
  • Short replies · 55 draws of 703 won12 won
  • Entities · 45 draws of 502 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

Realtime Whisper 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 Realtime Whisper scores 2.63% and Zoom Scribe Pro v2.1 2.35%, so Zoom Scribe Pro v2.1 makes fewer errors by 0.28 points. On the 300 licensed Ocular turns, GPT Realtime Whisper scores 2.16% and Zoom Scribe Pro v2.1 1.55%, so Zoom Scribe Pro v2.1 makes fewer errors by 0.61 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • No. Zoom Scribe Pro v2.1 finishes the transcript 586ms sooner. GPT Realtime Whisper has the final transcript 1.38s after the speaker stops and Zoom Scribe Pro v2.1 793ms, at the median. Both are measured on the same 206 streamed turns.

  • Zoom Scribe Pro v2.1 is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 586ms 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. GPT Realtime Whisper shows first text after 3.53% and Zoom Scribe Pro v2.1 after 3.87%, at the median.

Test your voice agent the same way.

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