Smallest Pulse vs Soniox STT-RT v5

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)
  • Pulse3.66% · 201ms
  • STT-RT v52.54% · 38ms

Soniox STT-RT v5 is ahead on both datasets together, the Pipecat Dataset and final-text delay, and Smallest Pulse on time to first text. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

PulseSTT-RT v5
  • Overall WER3.59%3.02%
  • Pipecat Dataset WER3.66%2.54%
  • Ocular Dataset WER3.46%3.92%
  • Time to first text1.06s1.20s
  • Final-text delay201ms38ms

Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide explains how word error rate is measured.

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.

PulseSTT-RT v5
  • ELO rating1005998–1011 · rank 6–181000986–1007 · rank 6–20
  • Expected win rate51%49%
  • Ocular turns WER · 141 draws of 19828 won29 won
  • Pipecat WER · 777 draws of 99978 won144 won
  • Semantic WER · 182 draws of 1988 won8 won
  • Phone line · 148 draws of 19728 won21 won
  • Call-center noise · 111 draws of 19740 won46 won
  • Babble noise · 98 draws of 19860 won40 won
  • TV noise · 122 draws of 19868 won8 won
  • Reverb · 145 draws of 19827 won26 won
  • Short replies · 40 draws of 7014 won16 won
  • Entities · 45 draws of 503 won2 won

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

Pulse vs STT-RT v5 FAQ

  • Soniox STT-RT v5 is more accurate on both datasets. On the 1,000 public Pipecat clips, Smallest Pulse scores 3.59% and Soniox STT-RT v5 3.02%, so Soniox STT-RT v5 makes fewer errors by 0.57 points. On the 300 licensed Ocular turns, Smallest Pulse scores 3.66% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 1.11 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. Smallest Pulse finishes the transcript 138ms sooner. Smallest Pulse has the final transcript 1.06s after the speaker stops and Soniox STT-RT v5 1.20s, at the median. Both are measured on the same 206 streamed turns.

  • It is a trade-off. Soniox STT-RT v5 makes fewer errors on real conversations, while Smallest Pulse finishes the transcript 138ms 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. Smallest Pulse shows first text after 3.46% and Soniox STT-RT v5 after 3.92%, at the median.

Test your voice agent the same way.

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