Gradium 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)
  • Gradium4.02% · 219ms
  • STT-RT v52.54% · 38ms

Soniox STT-RT v5 is ahead of Gradium 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

GradiumSTT-RT v5
  • Overall WER3.83%3.02%
  • Pipecat Dataset WER4.02%2.54%
  • Ocular Dataset WER3.47%3.92%
  • Time to first text1.78s1.20s
  • Final-text delay219ms38ms

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.

GradiumSTT-RT v5
  • ELO rating978973–983 · rank 15–211000986–1007 · rank 6–20
  • Expected win rate47%53%
  • Ocular turns WER · 157 draws of 19830 won11 won
  • Pipecat WER · 784 draws of 99960 won155 won
  • Semantic WER · 189 draws of 1987 won2 won
  • Phone line · 150 draws of 19829 won19 won
  • Call-center noise · 107 draws of 19819 won72 won
  • Babble noise · 101 draws of 19827 won70 won
  • TV noise · 144 draws of 19746 won7 won
  • Reverb · 135 draws of 19830 won33 won
  • Short replies · 51 draws of 7015 won4 won
  • Entities · 47 draws of 502 won1 won

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

Gradium vs STT-RT v5 FAQ

  • Soniox STT-RT v5 is more accurate on both datasets. On the 1,000 public Pipecat clips, Gradium scores 3.83% and Soniox STT-RT v5 3.02%, so Soniox STT-RT v5 makes fewer errors by 0.81 points. On the 300 licensed Ocular turns, Gradium scores 4.02% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 1.48 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • No. Soniox STT-RT v5 finishes the transcript 581ms sooner. Gradium has the final transcript 1.78s 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 is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 581ms 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. Gradium shows first text after 3.47% 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.