GPT Realtime Whisper 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)
  • Realtime Whisper2.16% · 543ms
  • STT-RT v52.54% · 38ms

Soniox STT-RT v5 is ahead on time to first text and final-text delay, and GPT Realtime Whisper 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

Realtime WhisperSTT-RT v5
  • Overall WER2.63%3.02%
  • Pipecat Dataset WER2.16%2.54%
  • Ocular Dataset WER3.53%3.92%
  • Time to first text1.38s1.20s
  • Final-text delay543ms38ms

Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide covers testing OpenAI Realtime API voice agents.

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.

Realtime WhisperSTT-RT v5
  • ELO rating10091005–1020 · rank 5–161000986–1007 · rank 6–20
  • Expected win rate51%49%
  • Ocular turns WER · 146 draws of 19827 won25 won
  • Pipecat WER · 840 draws of 99993 won66 won
  • Semantic WER · 183 draws of 1989 won6 won
  • Phone line · 145 draws of 19827 won26 won
  • Call-center noise · 122 draws of 19839 won37 won
  • Babble noise · 96 draws of 19855 won47 won
  • TV noise · 72 draws of 198123 won3 won
  • Reverb · 119 draws of 19825 won54 won
  • Short replies · 44 draws of 7014 won12 won
  • Entities · 46 draws of 503 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

Realtime Whisper vs STT-RT v5 FAQ

  • GPT Realtime Whisper is more accurate on the public clips. On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.63% and Soniox STT-RT v5 3.02%, so GPT Realtime Whisper makes fewer errors by 0.39 points. On the 300 licensed Ocular turns, GPT Realtime Whisper scores 2.16% and Soniox STT-RT v5 2.54%, with likely ranges of 1.92 to 2.41% 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 184ms sooner. GPT Realtime Whisper has the final transcript 1.38s 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 184ms 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. GPT Realtime Whisper shows first text after 3.53% 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.