Soniox STT-RT v5vsZoom Scribe
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- STT-RT v52.54% · 38ms
- Scribe1.97% · 118ms
Soniox STT-RT v5 is ahead on time to first text and final-text delay, and Zoom Scribe on the Pipecat Dataset. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Pipecat Dataset WER2.54%1.97%
- Ocular Dataset WER3.92%4.88%
- Time to first text1.20s1.67s
- Final-text delay38ms118ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
STT-RT v5 vs Scribe FAQ
Which is more accurate, Soniox STT-RT v5 or Zoom Scribe?
Zoom Scribe is more accurate on the public clips. On the 1,000 public Pipecat clips, Soniox STT-RT v5 scores 2.54% and Zoom Scribe 1.97%, so Zoom Scribe makes fewer errors by 0.58 points. On the eight licensed Ocular recordings, Soniox STT-RT v5 scores 3.92% and Zoom Scribe 4.88%, with likely ranges of 2.60 to 4.86% 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.
Zoom Scribe is more accurate on the public clips. On the 1,000 public Pipecat clips, Soniox STT-RT v5 scores 2.54% and Zoom Scribe 1.97%, so Zoom Scribe makes fewer errors by 0.58 points. On the eight licensed Ocular recordings, Soniox STT-RT v5 scores 3.92% and Zoom Scribe 4.88%, with likely ranges of 2.60 to 4.86% 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. Soniox STT-RT v5 finishes the transcript 80ms sooner. Soniox STT-RT v5 has the final transcript 38ms after the speaker stops and Zoom Scribe 118ms, at the median. Both are measured on the same 206 streamed turns.
Soniox STT-RT v5 finishes the transcript 80ms 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. Soniox STT-RT v5 shows first text after 1.20s and Zoom Scribe after 1.67s, at the median, so Soniox STT-RT v5 is 473ms sooner.