Deepgram Flux English 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)
  • Flux English3.90% · 108ms
  • STT-RT v52.54% · 38ms

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

Last updated Methodology by Dileep Chagam

Who is better at what

Flux EnglishSTT-RT v5
  • Overall WER4.00%3.02%
  • Pipecat Dataset WER3.90%2.54%
  • Ocular Dataset WER4.18%3.92%
  • Time to first text791ms1.20s
  • Final-text delay108ms38ms

Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.

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.

Flux EnglishSTT-RT v5
  • ELO rating956938–991 · rank 12–221000986–1007 · rank 6–20
  • Expected win rate44%56%
  • Ocular turns WER · 157 draws of 19518 won20 won
  • Pipecat WER · 761 draws of 99959 won179 won
  • Semantic WER · 179 draws of 1955 won11 won
  • Phone line · 159 draws of 19718 won20 won
  • Call-center noise · 84 draws of 19522 won89 won
  • Babble noise · 43 draws of 19720 won134 won
  • TV noise · 111 draws of 19646 won39 won
  • Reverb · 144 draws of 19617 won35 won
  • Short replies · 54 draws of 686 won8 won
  • Entities · 44 draws of 493 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

Flux English vs STT-RT v5 FAQ

  • Soniox STT-RT v5 is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux English scores 4.00% and Soniox STT-RT v5 3.02%, so Soniox STT-RT v5 makes fewer errors by 0.98 points. On the 300 licensed Ocular turns, Deepgram Flux English scores 3.90% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 1.36 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. Deepgram Flux English finishes the transcript 404ms sooner. Deepgram Flux English has the final transcript 791ms 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 Deepgram Flux English finishes the transcript 404ms 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. Deepgram Flux English shows first text after 4.18% 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.