Reson8 Resonant-1 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)
  • Resonant-12.10% · 235ms
  • STT-RT v52.54% · 38ms

Soniox STT-RT v5 is ahead on time to first text and final-text delay, and Reson8 Resonant-1 on both datasets together. The Pipecat Dataset and The Ocular Dataset are too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

Resonant-1STT-RT v5
  • Overall WER2.38%3.02%
  • Pipecat Dataset WER2.10%2.54%
  • Ocular Dataset WER2.93%3.92%
  • Time to first text2.40s1.20s
  • Final-text delay235ms38ms

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.

Resonant-1STT-RT v5
  • ELO rating10341021–1047 · rank 1–101000986–1007 · rank 6–20
  • Expected win rate55%45%
  • Ocular turns WER · 158 draws of 19835 won5 won
  • Pipecat WER · 842 draws of 99997 won60 won
  • Semantic WER · 188 draws of 1988 won2 won
  • Phone line · 155 draws of 19836 won7 won
  • Call-center noise · 118 draws of 19845 won35 won
  • Babble noise · 102 draws of 19857 won39 won
  • TV noise · 125 draws of 19769 won3 won
  • Reverb · 146 draws of 19840 won12 won
  • Short replies · 53 draws of 7015 won2 won
  • Entities · 48 draws of 502 won0 won

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

Resonant-1 vs STT-RT v5 FAQ

  • Reson8 Resonant-1 is more accurate on the public clips. On the 1,000 public Pipecat clips, Reson8 Resonant-1 scores 2.38% and Soniox STT-RT v5 3.02%, so Reson8 Resonant-1 makes fewer errors by 0.64 points. On the 300 licensed Ocular turns, Reson8 Resonant-1 scores 2.10% and Soniox STT-RT v5 2.54%, with likely ranges of 1.86 to 2.35% and 2.27 to 2.83%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • No. Soniox STT-RT v5 finishes the transcript 1.21s sooner. Reson8 Resonant-1 has the final transcript 2.40s after the speaker stops and Soniox STT-RT v5 1.20s, at the median. Both are measured on the same 206 streamed turns.

  • Soniox STT-RT v5 finishes the transcript 1.21s 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. Reson8 Resonant-1 shows first text after 2.93% 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.