Left gets fewer words wrong. Lower has the final text ready sooner.
Soniox STT-RT v5 is ahead on both datasets together, the Pipecat Dataset and final-text delay, and Deepgram Flux Multilingual on time to first text. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.
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.
Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out
Soniox STT-RT v5 is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.81% and Soniox STT-RT v5 3.02%, so Soniox STT-RT v5 makes fewer errors by 1.79 points. On the 300 licensed Ocular turns, Deepgram Flux Multilingual scores 4.96% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 2.41 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Soniox STT-RT v5 is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.81% and Soniox STT-RT v5 3.02%, so Soniox STT-RT v5 makes fewer errors by 1.79 points. On the 300 licensed Ocular turns, Deepgram Flux Multilingual scores 4.96% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 2.41 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Flux Multilingual finishes the transcript 402ms sooner. Deepgram Flux Multilingual has the final transcript 793ms 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 Multilingual finishes the transcript 402ms 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 Multilingual shows first text after 4.53% and Soniox STT-RT v5 after 3.92%, at the median.
Cekura runs these simulated calls on your agent and scores every one.